Manufacturing equipment control via predictive "sequence to sequence" models

A 'sequence-to-sequence' model using neural networks addresses manufacturing inconsistencies by predicting part properties and adjusting control parameters, ensuring consistent production outcomes.

JP2024545482AActive Publication Date: 2024-12-06LIVELINE TECHNOLOGIES INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024547169
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-10-15
Filing Date
2022-10-14
Publication Date
2024-12-06
Estimated Expiration
2042-10-14

AI Technical Summary

Technical Problem

Manufacturing systems face challenges in maintaining consistent measurable properties of produced parts due to variations in control and extrinsic parameters over time, which existing statistical techniques struggle to effectively predict and adjust.

Method used

Applying a 'sequence-to-sequence' model, particularly using recurrent neural networks and long-short-term memory networks, to analyze time-series data from manufacturing systems, predict future part properties, and adjust control parameters to maintain target values through a control agent.

Benefits of technology

Enhances the ability to consistently produce parts with desired properties by predicting and proactively adjusting control settings based on real-time data, reducing variations and improving manufacturing consistency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024545482000001_ABST
    Figure 2024545482000001_ABST
Patent Text Reader

Abstract

The one or more processors measure values ​​of control and extrinsic parameters of a manufacturing system and generate a feature set describing the evolution of a state space of the manufacturing system from time series data of sensors measuring values ​​of functional parameters of parts produced by the manufacturing system, the one or more processors also generate a predicted value of at least one of the feature parameters from the feature set, and modify at least one of the control parameters in accordance with the feature set and the predicted value to drive the predicted value towards a target value.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to control of manufacturing equipment. [CROSS REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of U.S. Provisional Application No. 63 / 256,344, filed October 15, 2021, the disclosure of which is incorporated herein by reference in its entirety. [Background technology]

[0002] Manufacturing control systems may respond to input signals by generating output signals that cause the equipment they control to operate in a particular manner. Summary of the Invention [Problem to be solved by the invention]

[0003] The manufacturing system includes one or more processors for generating a feature set describing the evolution of a state space of the manufacturing system in the frequency or time domain from time series data of sensors measuring values ​​of control and extrinsic parameters of the manufacturing system and measuring values ​​of functional parameters of parts manufactured by the manufacturing system, the one or more processors further generating from the feature set a predicted value of at least one of the functional parameters via a "sequence to sequence" model of the manufacturing system, and modifying, via a control agent, at least one of the control parameters according to the feature set and the predicted value to drive the predicted value towards a target value.

[0004] The method includes generating a feature set describing the evolution of a state space of the manufacturing system in the frequency or time domain from time series data of sensors measuring values ​​of control and extrinsic parameters of the manufacturing system and measuring values ​​of functional parameters of parts manufactured by the manufacturing system. The method also includes generating from the feature set a predicted value of at least one of the functional parameters via a "sequence to sequence" model of the manufacturing system, and modifying, via a control agent, at least one of the control parameters according to the feature set and the predicted value to drive the predicted value towards a target value. [Brief description of the drawings]

[0005] [Figure 1] FIG. 1 is a block diagram of a manufacturing system. [Diagram 2] FIG. 2 is a block diagram of a control system. [Diagram 3] FIG. 2 is a block diagram of a control system. [Figure 4] FIG. 4 is a block diagram of the manufacturing and control system of FIGS. 1, 2 and 3. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0006] Herein, an embodiment will be described. However, it should be understood that the disclosed embodiment is merely an example, and other embodiments may take various alternative forms. The figures are not necessarily to scale. Some features may be exaggerated or minimized to show details of specific components. Therefore, specific structural and functional details disclosed herein should not be interpreted as limiting, but merely as a representative basis for teaching those skilled in the art.

[0007] Various features illustrated or described with reference to any one embodiment may be combined with features illustrated or described in one or more other embodiments to produce embodiments not explicitly illustrated or described. The illustrated combinations of features provide representative embodiments for typical applications. However, various combinations and modifications of features consistent with the teachings of the present disclosure may be desired for particular applications or implementations.

[0008] "Sequence to sequence" models, especially recurrent neural networks, are typically used in natural language processing, such as machine translation, question answering, and text summarization. Here, the "sequence to sequence" framework is applied to manufacturing control problems, where a myriad of manufacturing conditions (e.g., temperature, pressure, current flow, etc.) that affect the values ​​of measurable properties such as stiffness, thickness, and length change over time, with the goal of producing products with more consistent measurable properties.

[0009] Machines used for mass production often have control parameters that affect the measurable properties of the resulting parts. To give a simple example, a stamping machine may apply a certain amount of pressure for a certain amount of time to form metal into a desired shape. Thus, the stamping machine's ability to repeatedly produce the same desired shape depends on this pressure and time. If the values ​​of these control parameters change over time, a part made an hour earlier may have a slightly different shape than a part made an hour later, resulting in less consistency between parts.

[0010] In this example, the actual applied pressure may be a function of the power supplied to the stamping machine for a given pressure setting. Thus, variations in the power supplied may lead to variations in the applied pressure even though the pressure setting does not change. Thus, variations in the power supplied may be coupled with variations in the part shape, albeit with a time lag in between. That is, considering the processing time associated with the stamping machine, a change in the power supplied at time zero may manifest itself as a deviation from the desired shape at time 42 seconds. If it is possible to predict the effect of a sudden change in the power supplied on the part shape, then the pressure setting can be strategically altered to offset such changes. Specifically, if a decrease in power is expected, the pressure setting can be increased accordingly. If an increase in power is expected, the pressure setting can be decreased accordingly, etc.

[0011] Statistical techniques such as statistical process control are commonly used to monitor and control manufacturing processes with the goal of producing less waste and more conforming products. In complex manufacturing processes, these techniques may have limited effectiveness. Machines used for mass production may have hundreds, if not thousands, of control parameters (and extrinsic parameters) that affect the measurable properties of the resulting manufactured part, with the number being in the tens (e.g., 20). The ability to predict the effect of changes in control and extrinsic parameters on the measurable properties of the part is thus a complex endeavor.

[0012] As mentioned above, machine learning techniques commonly used in natural language processing have been found to be well suited to the task of predicting the effect that instantaneous changes to a large number of parameters may have on measurable characteristics of a part. These predictions can be used as feedback to control the process to produce more consistent part outcomes, even as input (including exogenous) parameters change.

[0013] Roughly speaking, recurrent neural networks store inputs via an internal memory, allowing them to handle continuous data, such as time series data that indicate ambient conditions, control inputs to manufacturing equipment, or measurable characteristics of parts produced by the manufacturing equipment. This internal memory allows the recurrent neural network to keep track of information about the inputs it receives and predict what will happen next. That is, the recurrent neural network adds the immediate past to the present. Thus, a recurrent neural network has two inputs: the present and the recent past. Weights are applied to the present and recent past inputs. These weights may be adjusted for gradient descent or backpropagation. Furthermore, the mapping from input to output does not have to be one-to-one.

[0014] Long short-term memory networks are an extension of recurrent neural networks. Long short-term memory allows recurrent neural networks to store inputs for longer periods of time in what is called a memory that can be read, written, and deleted. This memory can decide to store or delete information based on the importance assigned to the information. The importance of certain information can be learned over time by the long short-term memory. A typical long short-term memory has sigmoid input, forget, and output gates. These decide whether to accept a new input, delete it, or allow the new input to affect the current time step output.

[0015] A sequence to sequence model can be built using recurrent neural networks. A common sequence to sequence structure is the encoder-decoder structure, which has two main parts: an encoder and a decoder. The encoder and decoder can be, for example, long- and short-term memory models, respectively. Other such models, such as the transformer model, are also possible. The encoder reads the input sequence and summarizes the information into an internal state or context vector. The encoder output is discarded and the internal state is preserved, which helps the decoder to make accurate predictions.

[0016] The initial state of the decoder is initialized to the final state of the encoder, i.e., the internal state vector of the last cell of the encoder is input to the first cell of the decoder. In the initial state, the decoder can start generating an output sequence.

[0017] The above and similar concepts have been adapted for use in manufacturing. Long-term and short-term encoder-decoder models, transformers (e.g., bidirectional encoder representations from transformers, pre-trained generated transformer 3s, etc.), or other models may form the basis of a “sequence to sequence” model trained to interpret time series data describing ambient conditions and manufacturing operations and predict corresponding part characteristics. The time series data may include actual control parameter values ​​(e.g., current, machine revolutions per minute, machine pressure, machine temperature, etc.) and extrinsic parameter values ​​(e.g., ambient temperature, humidity, etc.), changes in these values ​​over predefined periods, and other relevant data, and may be pre-processed using various digital signal processing techniques (e.g., Fourier analysis, wavelet analysis, etc.) to generate a feature set (a set of all possible configurations) that describes the evolution of the state space of the manufacturing equipment in the frequency and / or time domain. For a given application, the specific set of digital signal processing techniques may be determined using standard methodologies including simulation, trial and error, etc.

[0018] With reference to FIG. 1, a manufacturing system 10 may include manufacturing equipment 12 (e.g., extruders, presses, etc.) that physically or virtually produces (e.g., assembles, creates, etc.) a manufactured part 14 (e.g., tubes, panels, etc.). The manufacturing system 10 may also include one or more ambient condition (extrinsic) sensors 16, current sensors 18 (e.g., motor drive current sensors, etc.), voltage sensors 20 (e.g., internal temperature sensors, etc.), one or more additional sensors 22 (e.g., conveyor speed sensors, percent proportional, integral, derivative output sensors, etc.), one or more property sensors 24 (e.g., differential pressure sensors, part dimension sensors, material rate sensors, etc.), and a database 26 (e.g., relational database, time series database, etc.). The ambient condition sensors 16 measure one or more ambient conditions (e.g., humidity, temperature, etc.) in the vicinity of the manufacturing equipment 12. The current and voltage sensors 18, 20 measure the current and voltage supplied to the manufacturing equipment 12. The additional sensors 22 measure other control parameters of the manufacturing equipment 12. The property sensors 24 measure various characteristic parameters (eg, length, stiffness, thickness, etc.) of the manufactured part 14 .

[0019] These detection values ​​can be reported to the database 26 in sequence. 0 At time t 1 , where each of the sensors 16, 18, 20, 22, 24 detects and reports its value to the database 26. Thus, the database 26 receives time series data describing ambient conditions and control parameter values ​​associated with the operation of the manufacturing equipment 12, as well as characteristic parameter values ​​associated with the manufactured parts 14 produced by the manufacturing equipment 12. Such an arrangement can be used to collect vast amounts of data for learning purposes.

[0020] Various transformations (e.g., data cleansing, bandpass filtering, convolution, principal component analysis, wavelet transform, etc.) can be performed on the time series data held in database 26 to generate a streaming feature set spanning a relevant state space that describes the evolution of the manufacturing process associated with manufacturing equipment 12. In one example, data cleansing includes backfilling, forward filling, and / or removal of null values ​​to ensure that the time series data does not have missing or poorly filled in features. After data cleansing, principal component analysis can be performed to maximize the amount of useful information while minimizing the number of features. If the original data set includes pressure, temperature, and drive power, which all have identical response information, principal component analysis will compact the data set while maintaining the response information, for example, so that the pressure value is used for continuing the transformation and training the process while the temperature and drive power values ​​are ignored. Other transformation operations may be performed further, but are not required. Other transformation steps may be performed further, but are not required. At any point in time, the combined transformed data represents the maximum amount of state information for manufacturing system 10. The relevant state space can be iteratively identified during model training and evaluation.

[0021] Referring to FIG. 2, one or more processors 28 may implement a long-term and short-term encoder-decoder model 30 (or other suitable model) trained on at least a portion of the streaming feature set from database 26. For example, a recurrent neural network that links one machine to another iterates the weights of the model until a gradient, which represents the change in the model's loss function (e.g., squared error loss) per change in the model's weights, asymptotically approaches zero. The weights of the recurrent neural network may be randomly seeded. The model may have a variety of depths and widths depending on the number of features present in a particular manufacturing line and the complexity of the manufacturing line's dynamic behavior. An example model may have two layers with 256 memory units. An adaptive moment estimation (Adam) optimizer may be used to perform gradient descent with a variable learning rate. Other optimizers, such as Adamax, are also contemplated.

[0022] For example, 60 minutes, 600 minutes, or 6000 minutes of the streaming feature set may be used to train the long-term and short-term encoder-decoder model 30 to recognize relationships between the detected ambient condition and control parameter values ​​of the sensors 16, 18, 20, 22 and the resulting detected feature parameter values ​​of the characteristic sensor 24. Once properly trained, the model 30 can predict future feature parameter values ​​of the manufactured part 14 from the streaming feature set.

[0023] 1 and 3, the one or more processors 28 may further implement a control agent 32 trained against the model 30 and the streaming feature set from the database 26. Prior to training of the control agent 32, the model 30 (or other source) may inform the control agent 32 of the control limits of the manufacturing equipment 12 that may be simulated by the model 30. The control limits may include, for example, the operating pressure range of the press (300 psi to 500 psi), the operating temperature range of the drying oven (50° C. to 80° C.), etc. Additionally, the control agent 32 may receive target feature parameter values ​​of the manufactured part 14 (e.g., target length=3 cm, target stiffness=5 N / m, etc.). During training of the control agent 32, the model 30 and the control agent 32 may each synchronously receive the same portion of the streaming feature set from the database 26 to simulate feedback from the sensors 16, 18, 20, 22, 24 during a manufacturing run. This enables the model 30 to generate predicted feature parameter values ​​of the simulated manufactured part and report them to the control agent 32. The control agent 32 can then instruct the model 30 to take control actions to change the control settings within the control limits. In a first iteration, assuming the operating pressure of the press simulated by the model 30 is 310 psi and the operating temperature of the drying oven simulated by the model 30 is 62° C., the control agent 32 can increase one by some amount and decrease the other by some amount to learn how such changes affect the predicted feature parameter values ​​from the model 30 relative to the target feature parameter values. The amount of change can be arbitrary or can follow a predetermined rule. The control agent 32 can perform thousands, if not millions, of such iterations in a relatively short period of time to train itself on how it can change the control settings of the manufacturing tool 12 to keep the predicted feature parameter values, and therefore the actual feature parameter values, at or near the target feature parameter values ​​as the values ​​from the sensors 16, 18, 20, 22, 24 change.

[0024] 4, once the control agent 32 has been properly trained (e.g., the error between the predicted and target feature parameter values ​​is within some predetermined range, such as 5%), one or more processors 28 may be deployed within the manufacturing system 10 to receive the live data output by the sensors 16, 18, 20, 22, 24 and pre-process the data using the various transformations (e.g., data cleansing and principal component analysis) described above in order to generate a live streaming feature set spanning the relevant state space describing the evolution of the manufacturing process associated with the manufacturing equipment 12. Similar to above, the now trained control agent 32 may then instruct the manufacturing equipment 12, based on the live streaming feature set and the corresponding predicted feature parameter values, to take control actions to modify control settings within control limits in order to maintain the predicted feature parameter values, and therefore the actual feature parameter values, at or near the target feature parameter values.

[0025] The algorithms, methods, or processes disclosed herein can be provided to or implemented by a computer, controller, or processing device, which may include a dedicated electronic control unit or a programmable electronic control unit. Similarly, the algorithms, methods, or processes can be stored in many forms, including, but not limited to, information permanently stored in a non-writable storage medium, such as a read-only memory device, and information mutably stored in a writable storage medium, such as a compact disk, random access memory, or other magnetic and optical media, as data and instructions executable by the computer or controller. The algorithms, methods, or processes can also be implemented in software executable objects. Alternatively, the algorithms, methods, or processes can be embodied in whole or in part using suitable hardware components, such as application specific integrated circuits, field programmable gate arrays, state machines, or other hardware components or devices, or a combination of firmware, hardware, and software components.

[0026] Although exemplary embodiments have been described above, it is not intended that these embodiments describe all possible forms encompassed by the scope of the claims. The words used herein are words of description rather than limitation, and it is understood that various changes may be made without departing from the spirit and scope of the disclosure.

[0027] As mentioned above, features of various embodiments may be combined to create further embodiments of the invention not explicitly described or illustrated. Although various embodiments may be described as offering advantages or being preferred over other embodiments or prior art implementations with respect to one or more desired characteristics, those skilled in the art will recognize that one or more features or characteristics may be compromised to achieve desired overall system attributes that depend on the particular application and implementation. These attributes include, but are not limited to, cost, strength, durability, life cycle cost, marketability, appearance, packaging, size, serviceability, weight, manufacturability, ease of assembly, and the like. Thus, an embodiment described as being less desirable than other embodiments or prior art implementations with respect to one or more characteristics is not outside the scope of this disclosure and may be desirable for a particular application.

Claims

1. 1. A manufacturing system comprising: One or more processors generating a feature set describing the evolution of a state space of the manufacturing system in the frequency or time domain from time series data of sensors measuring values ​​of control parameters and extrinsic parameters of the manufacturing system and measuring values ​​of functional parameters of parts manufactured by the manufacturing system; generating from said feature set, via a "sequence to sequence" model of said manufacturing system, a prediction of at least one of said functional parameters; and programmed to modify, via a control agent, at least one of the control parameters in accordance with the feature set and the predicted value to drive the predicted value toward a target value.

2. 2. The manufacturing system of claim 1, wherein the one or more processors are further programmed to train the sequence to sequence model against a historical feature set of the manufacturing system.

3. 2. The manufacturing system of claim 1, wherein the one or more processors are further programmed to train the control agent against past feature sets and corresponding predictions from the "sequence to sequence" model.

4. 2. The manufacturing system of claim 1, wherein the "sequence to sequence" model is an encoder-decoder model.

5. 5. The manufacturing system of claim 4, wherein the encoder-decoder model includes a long short-term memory model.

6. 1. A method comprising: generating a feature set describing the evolution of a state space of a manufacturing system in the frequency or time domain from time series data of sensors measuring values ​​of control and extrinsic parameters of the manufacturing system and values ​​of functional parameters of parts manufactured by said manufacturing system; generating from the feature set a prediction of at least one of the functional parameters via a "sequence to sequence" model of the manufacturing system; and altering, via a control agent, at least one of the control parameters according to the feature set and the predicted value to drive the predicted value towards a target value.

7. The method of claim 6 , further comprising training the sequence to sequence model against a historical feature set of the manufacturing system.

8. The method of claim 6 , further comprising training the control agent on past feature sets and corresponding predictions from the sequence to sequence model.

Citation Information

Patent Citations

  • Method and device for controlling a production process

    DE102019208922A1

  • Robust adjustment device and model creation method

    JP2020003893A

  • Information processing device, information processing method and program

    JP2021030407A

  • Convolutional neural network evaluation of additive manufacturing images and additive manufacturing systems based on this

    JP2021504197A

  • Production system, information processing method, and production method

    US20200293011A1