Continuous monitoring, proactive warning, and control of key performance indicator variables.

Abstract

A method, system, and computer program product are directed to collecting, by a computer system, sensor data of a manufacturing system, the sensor data being measured at intervals shorter than a time interval of a measurement of interest in the manufacturing system. The sensor data is determined to have a relationship with the measurement of interest. A synthetic measurement of interest is generated at intervals shorter than the time interval based on the relationship. A pre-alert to the measurement of interest is automatically generated based on the synthetic measurement of interest at intervals shorter than the time interval.

Description

[Technical Field]

[0001] The present invention generally relates to computer systems, and more specifically to computer implementations, computer systems, and computer program products configured and arranged to provide continuous monitoring, advance warning, and control of key performance indicator variables of a process having infrequently measured and time-aggregated values. [Background technology]

[0002] Manufacturing is the production of products for use or sale using labor, machinery, tools, and chemical or biological processing or formulation. While manufacturing can encompass a wide range of activities from mechanical to high-tech, it is primarily applied to industrial design, which transforms raw materials, including chemicals from primary industries, into final products on a large scale. The manufacturing process encompasses all stages from raw materials to the final product. The manufacturing process begins with product design and specifications for the materials that comprise the product. These materials are then transformed through the manufacturing process to become the necessary components. Modern manufacturing includes all the intermediate stages required for the production and integration of product components. While it is possible to test samples and products chronologically to check quality, samples and products in the manufacturing process need to be tested in a more granular manner to identify potential problems early before normal measurements. [Overview of the Initiative]

[0003] Embodiments of the present invention relate to a computer implementation method for providing continuous monitoring, advance warning, and control of key performance indicator variables of a process having infrequent, time-aggregated measurements. A non-limiting example of a computer implementation method includes a computer system collecting sensor data from a manufacturing system. The sensor data is measured at intervals shorter than the time intervals of the target measurement in the manufacturing system. The sensor data is determined to be related to the target measurement. The computer implementation method includes the computer system generating a composite target measurement at intervals shorter than the time intervals based on the relationship. The computer implementation method also includes the computer system automatically generating advance warnings for the target measurement based on the composite target measurement at intervals shorter than the time intervals.

[0004] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent and temporally aggregated measurements by generating synthetic target measurements at shorter intervals than normal target measurements. Thus, the computer implementation method described above efficiently provides early warning indicators regarding the target sample before the normal measurement process, thereby enabling early identification and mitigation of potential problems. Furthermore, the frequency of target measurements is often beyond the control of the system designer, for example, because performing target measurements more quickly would be too costly or impossible.

[0005] In addition to or alternative to one or more of the features described above or below, further embodiments of the present invention may include cases where one or more settings related to the manufacturing system are automatically modified based on the measurement values ​​to be synthesized, in response to prior warnings regarding the measurement values.

[0006] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent and temporally aggregated measurements by adjusting setpoints based on the synthesized measurement values, but prior to the normal measurement process.

[0007] In addition to, or alternative to, one or more features described above or later, further embodiments of the present invention may include cases in which one or more control components related to a manufacturing system are automatically corrected based on the synthesized measurement value in response to a prior warning for the measurement value.

[0008] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent and temporally aggregated measurements by adjusting control components based on the synthesized measurement value, but prior to the normal measurement process.

[0009] In addition to or alternative to one or more features described above or later, further embodiments of the present invention may include cases where the prior warning is generated in response to the composite measurement being outside a predetermined range.

[0010] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent and temporally aggregated measurements by enabling pre-warning based on composite target measurements prior to the normal measurement process.

[0011] In addition to or alternative to one or more features described above or later, further embodiments of the present invention may include modifications to the manufacturing system to move the measurement values ​​to be synthesized within a predetermined range.

[0012] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent and time-aggregated measurements by modifying the manufacturing system based on the synthesized target measurements prior to the normal measurement process.

[0013] In addition to or as an alternative to one or more features described above or later, further embodiments of the present invention may include cases where the measurement of interest is a quality-related variable corresponding to the outward flow in the physical material process of a manufacturing system. The measurement of interest has a non-instantaneous and time-intensive nature, resulting from equal sample amounts being collected at multiple points in time over a time interval and mixed in a container measured at the end of the time interval, thereby obtaining the measurement of interest.

[0014] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with infrequent, time-aggregated measurements by generating a synthetic target measurement as an instantaneous measurement preceding an inherently non-instantaneous, time-aggregated target measurement.

[0015] In addition to or alternative to one or more features described above or later, further embodiments of the present invention may include cases where the target measurement is a hybrid measurement of the aggregated total amount of the sample. The composite target measurement is a generated value at a point in time based on sensor data, and is not a measurement of the aggregated total amount of the sample, but rather represents the state of individual sample amounts at a point in time within a time interval.

[0016] In addition to one or more of the features described above or below, the computer implementation method provides an improvement over known methods for monitoring / key performance indicator variables with low-frequency, time-aggregated measurements by not relying on hybrid measurements of the aggregated total amount of samples.

[0017] Other embodiments of the present invention implement the features of the above-described method in a computer system and a computer program product.

[0018] Additional technical features and advantages are realized by the technology of the present invention. Embodiments and aspects of the present invention are described in detail herein and are considered part of the claimed subject matter. For a better understanding, please refer to the detailed description and the drawings.

[0019] The specific content of the exclusive rights described herein is particularly pointed out and clearly claimed in the claims at the conclusion of the specification. The foregoing and other features and advantages of embodiments of the present invention will be apparent from the following detailed description taken in conjunction with the accompanying drawings.

Brief Description of the Drawings

[0020] [Figure 1] FIG. is a block diagram of an exemplary computer system for use in combination with one or more embodiments of the present invention. [Figure 2] FIG. shows a block diagram of a system for providing continuous monitoring, early warning, and control of process key performance indicator variables having low-frequency and time-intensive measurements in accordance with one or more embodiments of the present invention. [Figure 3] FIG. shows further details of the computer system of FIG. 2 in accordance with one or more embodiments of the present invention. [Figure 4] FIG. shows a flowchart of a computer-implemented process for continuous monitoring, early warning, and control of process key performance indicator variables having low-frequency and time-intensive measurements in a manufacturing system in accordance with one or more embodiments of the present invention. [Figure 5] FIG. shows a diagram modeling the instantaneous quality of an unknown potential measurement in a measurement system in accordance with one or more embodiments of the present invention. [Figure 6] FIG. shows an exemplary representation of the model architecture of a model in accordance with one or more embodiments of the present invention. [Figure 7]This is a flowchart of a computer implementation method for providing continuous monitoring, advance warning, and control of process key performance indicator variables having infrequently measured and time-aggregated values ​​in a manufacturing system, according to one or more embodiments of the present invention. [Figure 8] This figure shows a cloud computing environment according to one or more embodiments of the present invention. [Figure 9] This figure shows an abstraction model layer according to one or more embodiments of the present invention. [Modes for carrying out the invention]

[0021] One or more embodiments of the present invention provide a computer implementation method, computer system, and computer program product for determining, inferring, or both, a composite / estimated quality measurement for a sample of interest from available sensor data. One or more embodiments generate a composite / estimated quality measurement for a sample of interest from available sensor data prior to the normal measurement of interest. Thus, one or more embodiments of the present invention provide an early indicator of the sample of interest prior to the normal measurement process, thereby enabling the early identification and mitigation of potential problems.

[0022] The measurement of interest, which is a quality measure, is collected regularly at a consistent frequency. There is information about how the target sample, which is the subject of the measurement of interest, is collected and measured. The system of interest, for example, a manufacturing system, is equipped with various sensors that collect data at a much higher frequency than the time-aggregated quality measurements of the target sample. One or more embodiments of the present invention improve the timeliness of information regarding the output quality of the target sample via synthesized / estimated quality measurements without performing any further measurements in the manufacturing system.

[0023] Turning to Figure 1, a computer system 100 according to one or more embodiments of the present invention is generally shown. The computer system 100 may be an electronic computer framework that includes, employs, or both, any number and combination of computing devices and networks utilizing various communication technologies, as described herein. The computer system 100 may be easily scalable, extensible, and modular, and may have the ability to be changed to different services or to reconfigure some functions independently of others. The computer system 100 may be, for example, a server, desktop computer, laptop computer, tablet computer, or smartphone. In some examples, the computer system 100 may be a cloud computing node. The computer system 100 can be described in the general context that computer system executable instructions, such as program modules, are executed by the computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc., that perform a specific task or implement a specific abstract data type. The computer system 100 may be practiced in a distributed cloud computing environment where tasks are performed by remote processing devices linked over a communication network. In a distributed cloud computing environment, program modules can be located on storage media of both local and remote computer systems, including memory storage devices.

[0024] As shown in Figure 1, the computer system 100 has one or more central processing units (CPUs) 101a, 101b, 101c, etc. (collectively or commonly referred to as processor 101). The processor 101 can be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The processor 101, also called a processing circuit, is connected to the system memory 103 and various other components via the system bus 102. The system memory 103 may include read-only memory (ROM) 104 and random-access memory (RAM) 105. The ROM 104 is connected to the system bus 102 and may include a basic input / output system (BIOS) or its successor, such as a Unified Extensible Firmware Interface (UEFI), which controls certain basic functions of the computer system 100. RAM is read-write memory connected to the system bus 102 for use by the processor 101. The system memory 103 provides a temporary memory space for the operation of the instructions during operation. The system memory 103 may include random access memory (RAM), read-only memory, flash memory, or any other suitable memory system.

[0025] The computer system 100 includes an input / output (I / O) adapter 106 and a communication adapter 107 connected to a system bus 102. The I / O adapter 106 may be a small computer system interface (SCSI) adapter that communicates with a hard disk 108 or other similar component or both. The I / O adapter 106 and the hard disk 108 are collectively referred to as mass storage 110 in this specification.

[0026] Software 111 to run on the computer system 100 can be stored in mass storage 110. Mass storage 110 is an example of a tangible storage medium readable by the processor 101, and the software 111 is stored as instructions to be executed by the processor 101 to operate the computer system 100, as described below in relation to various figures. Examples of computer program products and the execution of such instructions are described in more detail below. A communication adapter 107 interconnects the system bus 102 with a network 112, which may be an external network, and the communication adapter 107 enables the computer system 100 to communicate with other such systems. In one embodiment, a portion of the system memory 103 and mass storage 110 together stores an operating system. The operating system may be any suitable operating system for coordinating the functions of the various components shown in Figure 1.

[0027] Additional input / output devices are shown as being connected to the system bus 102 via display adapter 115 and interface adapter 116. In one embodiment, adapters 106, 107, 115, and 116 may be connected to one or more I / O buses connected to the system bus 102 via an intermediate bus bridge (not shown). A display 119 (e.g., a screen or display monitor) is connected to the system bus 102 by display adapter 115. Display adapter 115 may include a graphics controller and video controller to improve performance for graphics-intensive applications. A keyboard 121, mouse 122, speaker 123, etc., can be interconnected to the system bus 102 via interface adapter 116. Interface adapter 116 may include, for example, a super I / O chip that integrates multiple device adapters into a single integrated circuit. Suitable I / O buses for connecting peripheral devices such as hard disk controllers, network adapters, and graphics adapters typically include common protocols such as PCI (Peripheral Component Interconnect) and PCIe (Peripheral Component Interconnect Express). Therefore, as configured in Figure 1, the computer system 100 includes processing capabilities in the form of a processor 101, storage capabilities including system memory 103 and mass storage 110, input means such as a keyboard 121 and a mouse 122, and output capabilities including a speaker 123 and a display 119.

[0028] In some embodiments, the communication adapter 107 can transmit data using any suitable interface or protocol, such as an Internet small computer system interface, among other things. The network 112 can be a cellular network, a wireless network, a wide area network (WAN), a local area network (LAN), or the Internet, among other things. An external computing device can connect to the computer system 100 via the network 112. In some examples, the external computing device may be an external web server or a cloud computing node.

[0029] It should be understood that the block diagram in Figure 1 is not intended to show that computer system 100 includes all the components shown in Figure 1. Rather, computer system 100 may include any suitable few or additional components not shown in Figure 1 (e.g., additional memory components, embedded controllers, modules, additional network interfaces, etc.). Furthermore, embodiments of computer system 100 described herein can be implemented with any suitable logic, and the logic referred herein may, in various embodiments, include any suitable hardware (e.g., among other things, a processor, embedded controller, or application-specific integrated circuit), software (e.g., among other things, an application), firmware, or any suitable combination of hardware, software, and firmware.

[0030] Figure 2 is a block diagram of a system 200 for providing continuous monitoring, advance warning, and control of process key performance indicator variables having infrequently measured and time-aggregated values, according to one or more embodiments of the present invention. System 200 includes one or more computer systems 202 connected to a manufacturing system 230. The manufacturing system 230 can operate using control theory that uses control dynamics systems in engineering processes and machines. The manufacturing system 230 can utilize automated process control in a continuous production process. Automated process control is a combination of the fields of control engineering and chemical engineering that use industrial control systems to achieve production levels of consistency, economy, and safety, and is widely implemented in industries such as petroleum refining, pulp and paper manufacturing, chemical processing, and power plants. The manufacturing system 230 may include various system components 232, which represent various parts of equipment used to convert inputs to target outputs, as known to those skilled in the art. System components 232 may include electrical equipment, mechanical equipment, chemical equipment, etc. System components 232 represent machines or equipment necessary to function as a manufacturing system 230 or a factory or both.

[0031] The manufacturing system 230 includes control components 234 (or control devices) used to control the functions of system components 232. Control components 234 relate to anything in the manufacturing system 230 that can be controlled to be changed, modified, or both. Exemplary control components 234 may include actuators, control values, relays, switches, etc. Setpoints 236 (also called setpoints) are used in the manufacturing system 230. Setpoints are desired or target values ​​for essential variables or process values ​​in the manufacturing system 230. Control components 234 may include one or more setpoints 236 that control the operation of each control component 234. Setpoints 236 can be modified to change the operation and settings of the control components 234. One or more control systems 240 are present in the manufacturing system 230. Control systems 240 are used to control the functions and operations of control components 234, thereby controlling the functions and operations of system components 232. Control systems 240 may be used to modify the setpoints 236 of the manufacturing system 230. The control system uses a control loop to manage, command, instruct, or regulate the operation of other devices or systems (e.g., control component 234), or a combination thereof. In the case of continuous modulation control, a feedback controller is used to automatically control a process or operation. The control system compares the value or state of the controlled process variable with a desired value or setpoint and applies the difference as a control signal to make the output of the process variable of the plant (e.g., manufacturing system 230) equal to the setpoint.

[0032] In the manufacturing system 230, quality measurements 250 are taken for the product in question, which may be at any desired stage of manufacturing. The quality measurements 250 are measurements of interest and are collected regularly at a consistent frequency from a predetermined single output of the system component 232. For example, quality measurements may be taken every "T" time (e.g., T = 12 hours, 24 hours, 1 week, etc.). In process industries, the quality of the output product must be maintained, which may include ensuring that all regulatory constraints, including federal standards set by regulatory bodies, are met. Often, this is done by regularly performing costly and time-consuming laboratory measurements based on aggregated samples collected over time. Depending on the results of the laboratory measurements, the quality of the product in question may be insufficient, or may violate regulatory constraints, or both. In any case, this would be a costly error. Therefore, quality measurements 250 are taken to meet predetermined requirements. The quality measurements 250 are true aggregated measurements. For example, quality measurement values ​​250 are based on small amounts collected over time (e.g., from system components 232) and combined in the same sample container 252. Thus, a single quality measurement value 250 consists of time-aggregated measurements of the sample / target product in the sample container 252, and the sample in the sample container 252 is a time-aggregated sample. Subsequent measurements of the time-aggregated quantity in the sample container 252 also have an additional delay.

[0033] The manufacturing system 230 includes various sensors 238 coupled to system components 232, which measure (i.e., collect) data at a much higher frequency than the measurements of the quality measurement 250. The control system 240 is coupled to the sensor 238 and can acquire measurements (i.e., sensor data) from the sensor 238. Sensor measurements can be taken at time intervals of T' (e.g., minutes), where T' is less than T. For example, sensor measurements by sensor 238 can be taken / acquired every 5 minutes, every 10 minutes, etc. Sensor measurements by sensor 238 can be taken / acquired every hour, every 2 hours, etc. The sensor measurements of sensor 238 do not measure the actual sample collected in the sample container 252. Rather, sensor 238 can provide measurements and readings of various instruments, materials, flows, etc., at various / different stages of the manufacturing process for producing the sample in the sample container 252. The sensor measurements and readings may be of any type of measurable value in or relating to the manufacturing system 230, or both. For example, the sensor measurements and readings may be for ore quality, temperature, density, flow rate, voltage, current, speed, rotations per minute, vibration, etc.

[0034] The computer system 202 is connected to the manufacturing system 230. The computer system 202 may be connected to the control system 240, the sensor 238, the control component 234, or the setpoint 236, or a combination thereof. In one or more embodiments, the control system 240 may include one or more control applications 242 configured to connect to the software application 204 of the computer system 202. The control application 242 may also monitor and control the system components, the control component 234, the setpoint 236, and the sensor 238, as will be understood by those skilled in the art. Further details of the computer system 202 are shown in Figure 3. In one or more embodiments, the computer system 202 may be implemented in or integrated with the control system 240, or both. The software application 204 may be implemented as software 111 running on one or more processors 101, as described in Figure 1. Similarly, the control application 242 may be implemented using software 111 configured to run on one or more processors 101. The elements of computer system 100 can be used in, integrated with, or both of the computer system 202 and the control system 240.

[0035] Figure 4 shows a flowchart of a computer-implemented process 400 according to one or more embodiments of the present invention, which provides continuous monitoring, advance warning, and control of process key performance indicator variables having infrequently measured and time-aggregated values ​​in a manufacturing process. The computer-implemented process 400 of Figure 4 can be implemented using the system 200 shown in Figure 2 and the computer system 202 shown in Figure 3. Accordingly, the computer-implemented process 400 will now be described with reference to the system 200 and computer system 202 of Figure 2.

[0036] In block 402, the software application 204 of the computer system 202 is configured to collect sensor data from the sensor 238 of the manufacturing system 230. The sensor data from sensor 238 is measured more frequently than the measurement of quality measurement value 250 (e.g., measured at shorter intervals or time T'). In one or more embodiments, the software application 204 can acquire sensor data from sensor 238 from the control application 242 of the control system 240. The sensor data from sensor 238 can be pushed to the software application 204 of the computer system 202, or pulled by the software application 204 of the computer system 202, or both. In one or more embodiments, the control system 240 may buffer and / or store the sensor data for each sensor 238 before sending the sensor data to the computer system 202. In one or more embodiments, the software application 204 can receive the sensor data from sensor 238 in real time, near real time, or both.

[0037] In block 404, the software application 204 of the computer system 202 is configured to slice / divide the sensor data of sensor 238 into blocks of sensor data (e.g., tensor slices), where different blocks correspond to different groups / periods of time of measurements acquired by sensor 238. In block 406, the software application 204 of the computer system 202 is configured to use blocks of sensor data (e.g., tensor slices) for different groups / periods as input to model 306, which is configured to determine a composite / estimated quality measurement of the manufacturing system 230. The composite / estimated quality measurement is generated more frequently than the measurements of the quality measurement 250. In other words, the composite / estimated quality measurement is generated more frequently than the measurements acquired for the quality measurement 250. This composite / estimated quality measurement also has less time lag or delay, or both, than the quality measurement 250, which is a physical measurement.

[0038] In block 408, the software application 204 of the computer system 202 is configured to check whether the composite / estimated quality measurement is within the normal range of the manufacturing system 230. The normal range is predetermined. The normal range may have a lower limit and an upper limit, and the composite / estimated quality measurement must remain within the lower and upper limits that are considered normal. If the composite / estimated quality measurement is within the normal range ("YES"), the flow proceeds to block 402, and monitoring continues. Continuous monitoring includes the continuous generation of composite / estimated quality measurement. If the composite / estimated quality measurement is outside the normal range ("NO"), the software application 204 is configured to issue a prior warning (e.g., notification 280) based on one or more composite / estimated quality measurement values ​​that have fallen outside the normal range. For example, the software application 204 may issue a warning to the control application 242 of the control system 240 and to the operator. The advance warning is an early indicator that there is a problem with the manufacturing system 230, including a potential problem with the sample in the sample container 252, before the period "T" for obtaining quality measurement values ​​250 of the sample in the sample container 252.

[0039] In block 412, the software application 204 of the computer system 202 is configured to modify one or more setting values ​​236 or one or more control components 234 or both in the manufacturing system 230. In one or more embodiments, the software application 204 can cause, instruct, or request a change to one or more setting values ​​236 or one or more control components 234 or both, or a combination thereof. In one or more embodiments, the software application 204 can communicate a request (or notification 280 or both) to the control system 240 so that the request causes the control application 242 of the control system 240 to modify the setting values ​​236 or one or more control components 234 or both. In one or more embodiments, for the sake of notification 280, the software application 204 can cause a value, operation, or function, or a combination thereof, associated with one or more setting values ​​236 or one or more control components 234 or both to be increased, decreased, or both.

[0040] As a result, the operation of the manufacturing system 230 is improved, and errors can be avoided based on the notification 280, which is a pre-warning. The composite / estimated quality measurement is generated using Model 306 at shorter intervals, shorter time periods, or both, than the measurement of the quality measurement 250. Thus, the composite / estimated quality measurement generated using the sensor data of sensor 238 provides an early indicator of the target sample collected in the sample container 252 before the normal quality measurement 250. As described herein, the quality measurement 250 is a delayed time summary based on the sample collected in the sample container 252, while the composite / estimated quality measurement is an instantaneous representation of the sample at any point in time shorter than the time "T" for acquiring / measuring the quality measurement 250. Thus, using the composite / estimated quality measurement at different points in time, the software application 204 is configured to generate / estimate more granular information about the true quality measurement 250 in order to enable early identification of potential problems in the manufacturing system 230 and thereby provide mitigation.

[0041] Figure 5 is a block diagram modeling the instantaneous quality of unknown potential measurements in a manufacturing system 230 according to one or more embodiments of the present invention. The unknown potential measurements are used to generate a composite / estimated quality measurement. Model 306 is a physical-based model related to the manufacturing system 230. In Figure 5, individual measurements / readings of different sensors 238 are shown by individual circles along the timeline. Each measurement / reading of sensor 238 is taken in an example within a time period shorter than the time between measurements taken for a quality measurement 250. The circles on timeline 502 represent quality measurement 250 taken at intervals or periods of time "T". For illustrative purposes, sensors 238 may include sensors A, B, through N, where N is the last sensor, and each sensor has multiple measurements on the timeline. Each circle on timeline 504 is an unknown potential result that can provide additional knowledge of the manufacturing system 230. The circle on timeline 504 is not measured in the manufacturing system 230, but is derived from the relationship between the sensor data of sensor 238 and the quality measurement value 250.

[0042] When training Model 306, the software application 204 uses historical data 310 (for example, stored in memory 308) to learn the relationship between sensor data and quality measurement values ​​250 of sensor 238 for the same period "T", and this process is repeated sequentially. The historical data 310 includes time-aligned historical sensor data and historical quality measurement values ​​250 of sensor 238. The historical data 310 stored in the database can be represented in numerous databases. The databases may contain hundreds, thousands, millions, or combinations thereof of documents, also known as "big data". In one or more embodiments, the enormous size of the historical data 310 in the database would require machine management, processing, and retrieval (such as a computer system 202) using, for example, computer-executable instructions, and the historical data 310 in the database could not be substantially managed, stored, analyzed, or processed, or a combination thereof, in the human mind as discussed herein.

[0043] When training model 306, the software application 204 is configured to fit a regression model that relates high-frequency covariates (individual measurements of sensor data from sensor 238) over a measurement period "T" to delayed low-frequency measurements 250 (e.g., delayed low-frequency (lab) results) through unknown intermediate quality results on timeline 504. For illustrative purposes, y is a symbol representing the quality measurement 250, and y t This shows the value of the quality measurement 250 at time t. The unknown intermediate quality result at time t is obtained by the initially unknown relationship f() and the unknown output q t =f(X t-T’ It is written as :t). Function y t =g(q t-T:t) has known relationships and unknown inputs (e.g., an unknown input q over a time period tT to t). Model 306 learns a function f() and uses f() during subsequent predictions. In one or more embodiments, the quality measurement 250 is based on a uniformly equal sample quantity over time, so the function g() is known, in which case Model 306 considers the average quality over an observation window "T". In this case, the final sample in the sample container 252 sent out for measurement consists of a uniform mixture over time, and the measurement in question results in an average measurement of quality.

[0044] During training, sensor data from sensor 238 (i.e., measured values / readings) are aligned to match the period "T" over which samples are collected in sample container 252, and quality measurements 250 of the collected samples in sample container 252 are obtained. Each quality measurement 250 is obtained for the collected samples in sample container 252, and the sample data from sensor 238 is used over the same period "T". Once model 306 is trained, model 306 can be used for each quality measurement 250 to generate a composite / estimated quality measurement (e.g., composite Y) at time intervals shorter than the period "T". The software application 204 applies the (trained) model 306 to a number of (possibly overlapping) windows of length T' of the covariates to predict an unknown intermediate result qt, and then processes these intermediate results (qt) to generate a mean quality measurement, which is a composite / estimated mean quality measurement for a particular time interval / window shorter than the period (T) of the original quality measurement 250. As described herein, this is particularly useful for providing more timely warnings to the system operator of the manufacturing system 230. In Figure 5, one or more blocks of sensor data (e.g., tensor slices) can be used to generate synthesized / estimated quality measurements for any desired or predetermined time window. Various regression models can be used to implement Model 306.

[0045] FIG. 6 is an exemplary representation of a model architecture 600 for model 306 according to one or more embodiments of the present invention. FIG. 6 shows the use of a neural network. A block of sensor data from sensor 238 represented by "X" is input into model 306 for the sum of the "m" blocks. The blocks of sensor data are grouped according to their matching batch / time groups. Sensor data from multiple sensors 238 are combined in each block. The blocks can be viewed as matrices (e.g., second-order tensors), and in each of these matrices, the columns consist of individual sensors where each row has a separate time point. For example, one block of sensor data (e.g., a tensor slice) is X t-T’-m+1:t-m+1 , another block of sensor data is X t-T’-m+2:t-m+2 , and through the block of sensor data which is X t-T’:t , it can be X t-T’:t . As described herein, the measurement of sensor data occurs in increments of time T'', and "m" is the number of blocks of sensor data (e.g., tensor slices) used to generate a single composite / estimated quality measurement value for the moment of time "t", which is the moment of time generally used to refer to the current time. Referring to FIG. 6, each block of sensor data is input into its own copy of a neural network representing the function f(). The multiple neural networks are identical copies of the same trained neural network responsible for implementing or capturing local variations or both as discussed herein. For each copy of the neural network, after inputting each block of sensor data into the function f(), the copy of the neural network outputs an unknown intermediate quality result q which is q t for each neural network. For example, for a neural network receiving each block of sensor data, one neural network generates q t-m+1 , and another neural network generates q t-m+2The neural network generates the final qt. A known aggregation function g() is used to aggregate the outputs from copies of the neural network. The output "y" of the known aggregation function g() is a single composite / estimated quality measure of the manufacturing system 230 for a given example of time "t", and the composite / estimated quality measure represents the status / state of the manufacturing system 230. The output of g() is the quality over a time period T (i.e., an aggregated quality measure over a time period from tT to t). The software application 204 can use Model 306 to generate composite / estimated quality measures for different examples of time "t", which may be shorter intervals than the time period "T" used for the quality measure 250.

[0046] Quality measurement 250 can be considered as a measurement of a process variable. Sensor data from sensor 238 can be considered as a covariate, or another process variable different from that process variable, or both. Using Model 306, the non-instantaneous nature of the process variable measurement takes the general form of a time-aggregated measurement. The time resolution and value of the time-aggregated measurement correspond to aggregation over a time interval using a general aggregation function (e.g., function g()) of the instantaneous values ​​of the variable over that interval. In contrast to the immediate case with online, offline, or both measurements, the time resolution and value of the measurement correspond to point-in-time.

[0047] The process variables in question (e.g., corresponding to quality measurement 250) are quality-related variables corresponding to the physical material process outflow stream. Measurements of quality-related variables are rarely available from the laboratory, and the non-instantaneous and time-aggregated nature of the quality measurement is due, in particular, to mixing / aggregating equal sample amounts drawn at multiple moments over a long period from the corresponding process outflow stream (e.g., into sample container 252), and then performing composite measurements on the aggregated total. As learned by Model 306, the non-instantaneous and time-aggregated nature of quality measurement 250 is due to an arbitrary identified general aggregate function applied over each aggregate interval corresponding to the historical process variable measurements (historical data 310), as a relationship determined in Model 306. The non-instantaneous and time-aggregated nature of quality measurement 250 is due to an unidentified general aggregate function applied uniformly over each aggregate interval corresponding to the historical process variable measurements, and is automatically learned by Model 306 from the historical data 310.

[0048] Continuous monitoring of process variables for quality measurement 250 is performed using model 306 by automatically estimating their instantaneous point-in-time values ​​(e.g., the value of qt). The relationships used to generate the point-in-time values ​​(e.g., composite / estimated quality measurement) are automatically learned from historical data by reconstructing a set of rare and time-interval aggregated historical ground truth measurements. Initially, unobserved, latent, point-in-time, immediate values ​​(e.g., qt) for process variables over the corresponding time intervals are obtained. t We construct the values ​​of q, and then use a general aggregate function (e.g., function g()) to obtain these latent estimates (e.g., q tThe value of is transformed. The potential estimate of a process variable at any given moment is the result of Model 306, which uses the values ​​of all covariates (e.g., blocks of sensor data from sensor 238) across a window of past process influences relative to each moment of time as input, where the length of this window (e.g., time "T'") is chosen as a hypervariable of the model, independently of the period between continuous (irregular) measurements of the process variable (e.g., period "T").

[0049] As shown in Figure 6, Model 306 can be a neural network with multiple layers of nonlinear activation functions, weights, and biases, and Model 306 takes both raw values ​​of all covariates (e.g., sensor data) over a window of historical process influence (e.g., time "T'") as input, as well as various time series features over a sequence of historical covariate values ​​in this window including mean, standard deviation, kurtosis, variance, etc. The automatic learning of a general aggregate function (e.g., function g()) is performed in a neural network with multiple layers of nonlinear activation functions, weights, and biases, and the general aggregate function (e.g., function g()) takes point-in-time latent estimates (e.g., q) as input. t-m+1 , q t-m+2 , and q t like q t Use the value of ).

[0050] Technical benefits and advantages of one or more embodiments include systems and methods that enhance consistency with the underlying physics of the manufacturing process. Estimated potential quality results (e.g., q t ) depends on sensor measurements over a shorter time range. Estimated quality results (e.g., q t This method can be accurately used to capture the long-term dynamics present in average quality measurements, effectively summarizing the local behavior of the process, and therefore the estimated quality outcome (e.g., q) tThis is used to generate synthetic / estimated quality measures. Knowing the potential quality outcomes allows for the formulation of other time-averaged values ​​that are more useful for ensuring process behavior than long-term averages.

[0051] Figure 7 is a flowchart of a computer-implemented process 700 for providing continuous monitoring, advance warning, and control of process key performance indicator variables having infrequently measured and time-aggregated values ​​in a manufacturing system 230, according to one or more embodiments of the present invention. The computer-implemented process 700 of Figure 7 can be implemented using the system 200 shown in Figure 2, along with the discussions in Figures 3 to 6.

[0052] In block 702, a software application 204 on the computer system 202 is configured to collect sensor data from the manufacturing system 230, where the sensor data is measured at intervals shorter than the time interval (e.g., period "T") of the target measurement (e.g., quality measurement 250) of the manufacturing system 230 (e.g., quality measurement 250), and the sensor data is determined to be related to the target measurement (e.g., quality measurement 250). For example, the software application 204 can collect sensor data from the control system 240, or directly from the sensor 238, or both.

[0053] In block 704, a software application 204 on the computer system 202 is configured to generate composite target measurements at intervals shorter than a time interval (e.g., time "T'") based on a relationship. For example, the relationship may include a relationship between a function f(), a function g(), and a quality measurement 250, where a block of sensor data ("X") is used as input. Model 306 may be used to generate composite target measurements at a given time to represent the quality measurement 250.

[0054] In block 706, a software application 204 on the computer system 202 is configured to automatically generate a prior warning (e.g., notification 280) for a composite target measurement based on a composite target measurement within an interval shorter than a time interval (e.g., time "T").

[0055] One or more setpoints 236 associated with the manufacturing system 230 are automatically corrected in response to a prior warning (e.g., notification 280) for a target measurement based on the combined target measurement. One or more control components 234 associated with the manufacturing system 230 are automatically corrected in response to a prior warning (e.g., notification 280) for a target measurement based on the combined target measurement. The prior warning (e.g., notification 280) is generated (by the computer system 202) because the combined target measurement is outside a predetermined range (e.g., a predetermined normal range). Changes are made to the manufacturing system 230 (e.g., caused, instructed, or both) to bring the combined target measurement within the predetermined range.

[0056] The target measurement (e.g., quality measurement 250) is a quality-related variable corresponding to the physical material process outflow stream of the manufacturing system 230, and the target measurement includes non-instantaneous, temporally aggregated characteristics obtained by mixing equal sample amounts in a container (e.g., sample container 252) where equal sample amounts are collected at multiple moments over a time interval (e.g., a period of time "T"), measured at the end of the time interval, and thereby obtaining the target measurement (e.g., quality measurement 250).

[0057] The target measurement (e.g., quality measurement 250) is a mixed measurement relating to the aggregated total amount of the sample (e.g., collected in sample container 252). The composite target measurement is a value generated for a given point in time based on sensor data, and is not a measurement of the aggregated total amount of the sample; rather, the composite target measurement represents the state of individual sample amounts at a given point in time within a time interval.

[0058] The target measurement (e.g., quality measurement 250) is a mixed measurement of the aggregated total amount of samples (e.g., collected in sample container 252). The aggregate function (e.g., aggregate function g()) that generates the mixed target measurement from equal sample amounts constituting the aggregated total amount is unknown and is automatically learned as a function of the target measurement over equal sample amounts. For known aggregate functions (g()), since the function is known in this case, the learning process incorporates this information as depicted in Figure 6, as previously described herein. In one or more embodiments, there may be unknown aggregate functions (i.e., the aggregate function (g()) is unknown), in which case g() may be unknown to the system designer / engineer. Therefore, the software application 204 or model 306 or both on the computer system 202 is configured to also learn g() in the process. In this case, the aggregate function g() in Figure 6 is replaced by another neural network whose parameters need to be learned. The composite measurement is a value generated at a certain point in time based on sensor data (e.g., from the manufacturing system 230) (e.g., via model 306 of software application 204), and is not a measurement of the aggregated total amount of the sample. Rather, the composite measurement represents the state of individual sample quantities of equal sample quantities (e.g., collected in sample container 252) at a point in time within a time interval (e.g., a period of time "T"). Note that the composite measurement is composite in the sense that it is based on the output of a trained model (f()). This could be a measurement at a certain point in time (i.e., instantaneous quality), or a new aggregate generated at a finer granularity (i.e., average quality over one hour), or both. In one embodiment, the measurement at a point in time may correlate (e.g., coincide or nearly coincide) with the time of the individual sample quantities, thereby providing insight into what happened in the manufacturing system 230, or its state at that time, or both.

[0059] The target measurement (e.g., quality measurement 250) is a composite measurement of the aggregated total volume of the sample (e.g., collected in a sample container 252). The aggregate function (e.g., aggregate function g()) that generates the composite target measurement from equal sample quantities constituting the aggregated total is known to be the average of the target measurement over equal sample quantities. The composite target measurement (e.g., via model 306 of software application 204) is a time-generated value based on sensor data and is not a measurement of the aggregated total volume of the sample. Rather, the composite target measurement represents the state of individual samples of equal sample quantities at a time point in time (e.g., a period of time "T").

[0060] The target measurement (e.g., quality measurement 250) is a composite measurement of the aggregated total volume of the sample (e.g., collected in sample container 252). The aggregate function (e.g., aggregate function g()) that generates the composite target measurement from equal sample quantities constituting the aggregated total volume is known from a user-specified function of the target measurement over equal sample quantities. The composite target measurement (e.g., via model 306 of software application 204) is a time-generated value based on sensor data and is not a measurement of the aggregated total volume of the sample. Rather, the composite target measurement represents the state of individual samples of equal sample quantities at a time point in time (e.g., a period of time "T").

[0061] While this disclosure includes a detailed description of cloud computing, it should be understood that the implementations of the teachings described herein are not limited to cloud computing environments. Rather, embodiments of the present invention can be implemented with any other type of computer environment that is currently known or may be developed in the future.

[0062] Cloud computing is a service delivery model that enables convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal administrative effort or interaction with service providers. This cloud model may include at least five characteristics, at least three service models, and at least four implementation models.

[0063] The characteristics are as follows:

[0064] On-demand self-service: Cloud consumers can unilaterally prepare computing power, such as server time and network storage, automatically as needed, without requiring human interaction with service providers.

[0065] Broad network access: Computing power is available over the network and accessible through standard mechanisms. This facilitates utilization by heterogeneous thin or thick client platforms (e.g., mobile phones, laptops, PDAs).

[0066] Resource pooling: A provider's computing resources are pooled and delivered to multiple consumers using a multi-tenant model. Various physical and virtual resources are dynamically allocated and reallocated as needed. Generally, consumers have a sense of location independence because they do not manage or know the exact location of the resources provided. However, consumers may be able to identify the location at a higher level of abstraction (e.g., country, state, data center).

[0067] Rapid Elasticity: Computing power can be prepared quickly and flexibly, allowing it to scale out automatically and immediately, and to be quickly released and scale in immediately. To consumers, the computing power available for preparation often appears unlimited and can be purchased in any quantity at any time.

[0068] Measured Services: Cloud systems leverage metric capabilities at a certain level of abstraction, appropriate for the type of service (e.g., storage, processing, bandwidth, active user accounts), to automatically control and optimize resource usage. Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.

[0069] The service model is as follows:

[0070] Software as a Service (SaaS): The functionality offered to consumers is the ability to use the provider's applications running on a cloud infrastructure. These applications can be accessed from various client devices via thin client interfaces such as web browsers (e.g., webmail). Consumers do not manage or control the underlying cloud infrastructure, including the network, servers, operating systems, storage, or even individual application functions, except for configuring a limited number of user-specific applications.

[0071] Platform as a Service (PaaS): The functionality offered to consumers is the ability to deploy applications they have created or acquired to cloud infrastructure using programming languages ​​and tools supported by the provider. Consumers do not manage or control the underlying cloud infrastructure, including networks, servers, operating systems, and storage, but they can control the deployed applications and, in some cases, the configuration of their hosting environment.

[0072] Infrastructure as a Service (IaaS): The functionality provided to consumers is the provision of processors, storage, networking, and other basic computing resources that enable consumers to deploy and run any software, including operating systems and applications. Consumers do not manage or control the underlying cloud infrastructure, but they can control the operating system, storage, and deployed applications, and in some cases, partially control certain network components (e.g., host firewalls).

[0073] The deployment model is as follows:

[0074] Private Cloud: This cloud infrastructure is operated exclusively for a specific organization. This cloud infrastructure can be managed by that organization or a third party and can reside on-premises or off-premises.

[0075] Community Cloud: This cloud infrastructure is shared by multiple organizations to support a specific community with common interests (e.g., mission, security requirements, policies, and compliance). This cloud infrastructure can be managed by the organization or a third party and can reside on-premises or off-premises.

[0076] Public Cloud: This cloud infrastructure is provided to a large number of people or large industry groups and is owned by organizations that sell cloud services.

[0077] Hybrid Cloud: This cloud infrastructure combines two or more cloud models (private, community, or public). While maintaining the unique entities of each model, they are bound together by standards or individual technologies to achieve data and application portability (e.g., cloud bursting for load balancing across clouds).

[0078] Cloud computing environments are service-oriented environments that emphasize statelessness, low coupling, modularity, and semantic interoperability. At the core of cloud computing is the infrastructure, which includes a network of interconnected nodes.

[0079] Referring to Figure 8, an exemplary cloud computing environment 50 is depicted. As shown, the cloud computing environment 50 includes one or more cloud computing nodes 10. Local computer devices used by cloud consumers, such as PDAs or mobile phones 54A, desktop computers 54B, laptop computers 54C, or automotive computer systems 54N, or a combination thereof, can communicate with these nodes. The nodes 10 can communicate with each other. The nodes 10 can be grouped physically or virtually (not shown) in one or more networks, such as the private, community, public, or hybrid clouds or a combination thereof. This allows the cloud computing environment 50 to provide infrastructure, platforms, or software as a service, or a combination thereof, without requiring cloud consumers to maintain resources on their local computer devices. Note that the types of computer devices 54A-N shown in Figure 8 are merely examples, and it should be understood that the computing nodes 10 and the cloud computing environment 50 can communicate with any type of electronic device via any type of network or network addressable connection (e.g., using a web browser) or both.

[0080] Referring now to Figure 9, a set of functional abstraction model layers provided by the cloud computing environment 50 (Figure 8) is shown. It should be understood that the components, layers, and functions shown in Figure 9 are illustrative only, and embodiments of the present invention are not limited to these. As illustrated, the following layers and corresponding functions are provided.

[0081] The hardware and software layer 60 includes hardware components and software components. Examples of hardware components include a mainframe 61, a reduced instruction set computer (RISC) architecture-based server 62, server 63, blade server 64, storage 65, and a network and network components 66. In some embodiments, the software components include network application server software 67 and database software 68.

[0082] The virtualization layer 70 provides an abstraction layer. From this layer, for example, the following virtual entities can be provided: virtual servers 71, virtual storage 72, virtual networks 73 including virtual private networks, virtual applications and operating systems 74, and virtual clients 75.

[0083] As an example, the management layer 80 can provide the following functions: Resource preparation 81 enables the dynamic procurement of computing resources and other resources used to perform tasks within the cloud computing environment. Metering and pricing 82 enables cost tracking as resources are used within the cloud computing environment and billing or invoicing for the consumption of these resources. As an example, these resources may include licenses for application software. Security enables not only protection of data and other resources but also identification and verification of cloud consumers and tasks. The user portal 83 provides consumers and system administrators with access to the cloud computing environment. Service level management 84 enables the allocation and management of cloud computing resources to ensure that requested service levels are met. Service Level Agreement (SLA) planning and execution 85 enables the pre-arrangement and procurement of cloud computing resources that are expected to be needed in the future in accordance with the SLA.

[0084] Workload layer 90 provides examples of the capabilities available to the cloud computing environment. Examples of workloads and capabilities available from this layer include mapping and navigation 91, software development and lifecycle management 92, virtual classroom education delivery 93, data analytics processing 94, transaction processing 95, and software applications implemented in workloads and capabilities 96 (e.g., software application 204, control application 242, model 306, etc.).

[0085] Various embodiments of the present invention are described herein with reference to the relevant drawings. Alternative embodiments of the present invention can be devised without departing from the scope of the invention. Various connections or positional relationships (e.g., above, below, adjacent, etc.) or combinations thereof between elements are defined in the following description and drawings. These connections or positional relationships or combinations thereof may be direct or indirect unless otherwise specified, and the present invention is not intended to limit in this respect. Thus, the connection of entities may refer to either a direct or indirect connection, and the positional relationship between entities may be a direct or indirect positional relationship. Furthermore, the various tasks and process steps described herein may be incorporated into more comprehensive procedures or processes having additional steps or functionalities not described in detail herein.

[0086] One or more methods described herein can be carried out using one or a combination of the following techniques, each well known in the art: discrete logic circuits (or more) having logic gates for implementing logic functions in data signals; application-specific integrated circuits (ASICs) having appropriate combinational logic gates; programmable gate arrays (or more) (PGAs); field-programmable gate arrays (FPGAs); and the like.

[0087] For the sake of brevity, prior art relating to the manufacture and use of aspects of the present invention may or may not be described in detail herein. In particular, various aspects of computing systems and specific computer programs for implementing the various technical features described herein are well known. Accordingly, for the sake of brevity, many prior implementation details are either briefly mentioned herein or omitted entirely without providing details of well known systems and / or processes.

[0088] In some embodiments, various functions or actions can be performed at a given location and / or in connection with the operation of one or more devices or systems. In some embodiments, a portion of a given function or action can be performed at a first device or location, and the remainder of the function or action can be performed at one or more additional devices or locations.

[0089] The terms used herein are for the purpose of describing specific embodiments only and are not intended to limit them. Where used herein, the singular forms "a," "an," and "the" are intended to include the plural form unless the context explicitly indicates otherwise. Where used herein, the terms "comprise" or "comprising" or both identify the presence of a described feature, integer, process, operation, element or component or combination thereof, but do not preclude the presence or addition of one or more other features, integers, processes, operations, element components or groups thereof or combination thereof.

[0090] All corresponding structures, materials, actions, and equivalents or step-plus-function elements in the following claims are intended to include any structures, materials, or actions to perform a function in combination with other claimed elements, as specifically claimed. This disclosure is presented for illustrative and explanatory purposes, but is not intended to be exhaustive or to be limited to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of this disclosure. The embodiments have been selected and described to best illustrate the principles and practical applications of this disclosure and to enable those skilled in the art to understand this disclosure in terms of various embodiments with various modifications suitable for the particular use to be intended.

[0091] The diagrams depicted herein are illustrative. Many variations are possible with respect to the diagrams or the steps (or operations) described therein without departing from the scope of this disclosure. For example, operations may be performed in a different order, or operations may be added, deleted, or modified. Furthermore, the term “joining” describes the presence of a signal path between two elements and does not imply a direct connection between elements without an intervening element / connection. All these variations are considered part of this disclosure.

[0092] The following definitions and abbreviations shall be used for interpretation of the claims and specification. Where used herein, the terms “comprises,” “comprising,” “includes,” “including,” “has,” “having,” “contains,” or “containing,” or other variations thereof, are intended to refer to non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus consisting of a list of elements may not necessarily be limited to those elements alone, and may include other elements not expressly listed or elements specific to such composition, mixture, process, method, article, or apparatus.

[0093] Furthermore, the term “exemplary” is used herein to mean “serving as an example, illustration, or diagram.” Any embodiment or design described herein as “exemplary” is not necessarily construed to be preferable or advantageous to other embodiments or designs. The terms “at least one” and “one or more” are understood to include any integer one or more, i.e., 1, 2, 3, 4, etc. The term “multiple” is understood to include any integer two or more, i.e., 2, 3, 4, 5, etc. The term “connection” may include both indirect and direct “connections.”

[0094] The terms “approximately,” “substantial,” “approximately,” and their variations are intended to include the degree of error associated with the measurement of a particular quantity based on the equipment available at the time of filing this application. For example, “approximately” may include a range of ±8%, 5%, or 2% of a given value.

[0095] The present invention may be a system, method, or computer program product or combination thereof, integrated at any possible level of technical detail. The computer program product may include a computer-readable storage medium storing computer-readable program instructions for causing a processor to perform aspects of the present invention.

[0096] A computer-readable storage medium can be a tangible device capable of holding and storing instructions used by an instruction execution device. Computer-readable storage media may, but are not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or appropriate combinations thereof. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, RAM, ROM, EPROM (or flash memory), SRAM, CD-ROM, DVD, memory stick, floppy disk, punch cards or grooved raised structures, and other mechanically encoded devices on which instructions are recorded, and appropriate combinations thereof. Computer-readable storage devices as used herein should not be interpreted as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses passing through optical fiber cables), or electrical signals transmitted through wires.

[0097] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network consists of copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, or edge servers, or a combination thereof. The network adapter card or network interface of each computing / processing device receives computer-readable program instructions from the network and transfers the computer-readable program instructions for storage on a computer-readable storage medium within each computing / processing device.

[0098] The computer-readable program instructions for performing the operation of the present invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk and C++ and procedural programming languages ​​such as the C programming language or similar programming languages. The computer-readable program instructions are executable as a standalone software package, either entirely on the user's computer or partially on the user's computer. Alternatively, they may be executable partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or to an external computer (for example, via the Internet using an Internet service provider). In some embodiments, for example, an electronic circuit including a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA) can execute computer-readable program instructions by personalizing them using state information of computer-readable program instructions in order to perform aspects of the present invention.

[0099] Aspects of the present invention are described herein with reference to flowcharts or block diagrams, or both, of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block in a flowchart or block diagram, or both, and any combination of blocks in a flowchart or block diagram, or both, can be implemented by computer-readable program instructions.

[0100] These computer-readable program instructions can be provided to a general-purpose computer, a special-purpose computer, or a processor of another programmable data processing device to generate a machine, such that instructions executed via the processor of a computer or other programmable data processing device generate means for implementing functions / operations specified in one or more blocks of a flowchart or block diagram or both. These computer-readable program instructions can also be stored in a computer-readable storage medium that can be connected to a computer, a programmable data processing device, or other device or combination of devices that function in a particular way, such that the computer-readable program instructions on which the instructions are stored constitute one of the outputs containing instructions that implement a mode of function / operation specified in one or more blocks of a flowchart or block diagram or both.

[0101] Computer-readable program instructions, like instructions that perform a function / action specified in one or more blocks of a flowchart or block diagram or both on a computer, other programmable device, or other device, can also be loaded into a computer, other programmable data processing device, or other device and perform a series of operational steps on the computer, other programmable device, or other device to produce a computer-implemented process.

[0102] The flowcharts and block diagrams in the figures illustrate the configuration, function, and operation of executable implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or part of an instruction, which constitutes one or more executable instructions for implementing a specified logical function. In some alternative embodiments, the functions shown in the blocks may differ from the order shown in the figures. For example, two blocks shown consecutively may actually be achieved as a single step, executed simultaneously, substantially simultaneously, partially or entirely in overlapping time, or the blocks may be executed in reverse order depending on the functions involved. It should also be noted that each block in a block diagram or flowchart diagram, or both, and any combination of blocks in a block diagram or flowchart diagram, or both, can be implemented by a special-purpose hardware-based system that performs a specified function or operation, or a combination of special-purpose hardware and computer instructions.

[0103] The descriptions of various embodiments of the present invention are presented for illustrative purposes only and are not intended to be exhaustive or to limit the disclosed embodiments. It will be apparent to those skilled in the art that many modifications and changes are possible without departing from the scope and spirit of the invention. The terms used herein have been selected to best describe the principles of the embodiments, their practical application to market-based technologies or technical improvements, or to enable those skilled in the art to understand the embodiments described herein.

Claims

1. The process involves collecting sensor data from a manufacturing system using a computer system, wherein the sensor data is measured at multiple intervals shorter than the time interval of the target measurement value of the manufacturing system, and the sensor data is determined to be related to the target measurement value. The computer system generates composite target measurement values ​​at one interval of the plurality of intervals based on the relationship, wherein the interval is shorter than the time interval, the computer system generates the composite target measurement values ​​using a machine learning model, the machine learning model includes a neural network trained on training data including historical sensor data and historical target measurement data, and training the machine learning model includes fitting a regression model that relates the sensor data measured at the plurality of intervals to the historical target measurement data at the time interval through unknown intermediate quality results based on a uniformly equal sample amount of the historical target measurement data over time, The computer system automatically generates a prior warning for the target measurement based on the combined target measurement within an interval shorter than the time interval, Computer implementation methods including

2. One or more setting values ​​related to the manufacturing system are automatically modified based on the measurement values ​​to be synthesized, in response to the prior warnings regarding the measurement values. The computer implementation method according to claim 1.

3. The computer implementation method according to claim 1, wherein one or more control components related to the manufacturing system are automatically corrected based on the measurement values ​​to be synthesized in response to the prior warnings regarding the measurement values ​​to be synthesized.

4. The aforementioned prior warning is generated when the measurement value to be synthesized is outside a predetermined range. The computer implementation method according to claim 1.

5. To move the measured values ​​of the synthesis target within a predetermined range, the manufacturing system is modified. The computer implementation method according to claim 1.

6. The aforementioned target measurement is a quality-related variable corresponding to the outward flow in the physical material process of the manufacturing system, and the aforementioned target measurement has a non-instantaneous and time-intensive nature due to the fact that equal sample amounts are collected at multiple points in time over a time interval, and equal sample amounts are mixed in a container measured at the end of the time interval, thereby obtaining the aforementioned target measurement. The computer implementation method according to claim 1.

7. The aforementioned measurement values ​​are mixed measurement values ​​of the aggregated total amount of the sample. The aforementioned composite measurement value is a value generated at a certain point in time based on the sensor data, and is not a measurement of the aggregated total amount of the sample, but rather represents the state of the individual sample quantities at a certain point in time within the time interval. The computer implementation method according to claim 6.

8. The aforementioned measurement values ​​are mixed measurement values ​​of the aggregated total amount of the sample. The aggregation function that creates the aggregated total from the equal sample quantities is unknown and is automatically learned as a function of the target measurement over the equal sample quantities. The aforementioned composite measurement value is a value generated at a certain point in time based on the sensor data, and is not a measurement value of the aggregated total amount of the sample. Rather, the composite measurement value represents the state of the individual sample amounts of the equal sample amounts at a certain point in time within the time interval. The computer implementation method according to claim 6.

9. The aforementioned measurement values ​​are mixed measurement values ​​of the aggregated total amount of the sample. The aggregation function used to create the aggregated total is known to be the average of the target measurements over the equal sample quantities. The aforementioned composite measurement value is a value generated at a certain point in time based on the sensor data, and is not a measurement value of the aggregated total amount of the sample. Rather, the composite measurement value represents the state of the individual sample amounts of the equal sample amounts at a certain point in time within the time interval. The computer implementation method according to claim 6.

10. The aforementioned measurement values ​​are mixed measurement values ​​of the aggregated total amount of the sample. The aggregation function that creates the aggregated total from the equal sample quantities is known from the user-specified function of the target measurement over the equal sample quantities, The aforementioned composite measurement value is a value generated at a certain point in time based on the sensor data, and is not a measurement value of the aggregated total amount of the sample. Rather, the composite measurement value represents the state of the individual sample amounts of the equal sample amounts at a certain point in time within the time interval. The computer implementation method according to claim 6.

11. Memory with computer-readable instructions, The system includes one or more processors for executing the computer-readable instructions, wherein the computer-readable instructions control the one or more processors and execute an operation, and the operation is The collection of sensor data from a manufacturing system, wherein the sensor data is measured at multiple intervals shorter than the time interval of the target measurement value of the manufacturing system, and the sensor data is determined to be related to the target measurement value. Based on the aforementioned relationship, the generation of a composite target measurement at one interval of the plurality of intervals, wherein the interval is shorter than the time interval, the composite target measurement is generated using a machine learning model, the machine learning model includes a neural network trained on training data including historical sensor data and historical target measurement data, and training the machine learning model includes fitting a regression model that relates the sensor data measured at the plurality of intervals to the historical target measurement data at the time interval through unknown intermediate quality results based on a uniformly equal sample amount of the historical target measurement data over time, Automatically generate a pre-warning for the target measurement based on the composite target measurement within the interval shorter than the aforementioned time interval, A system that includes this.

12. One or more setting values ​​related to the manufacturing system are automatically modified based on the measurement values ​​to be synthesized, in response to the prior warnings regarding the measurement values. The system according to claim 11.

13. The system according to claim 11, wherein one or more control components related to the manufacturing system are automatically corrected based on the measurement values ​​to be synthesized in response to the prior warnings for the measurement values ​​to be synthesized.

14. The aforementioned prior warning is generated when the measurement value to be synthesized is outside a predetermined range. The system according to claim 11.

15. To move the measured values ​​of the synthesis target within a predetermined range, the manufacturing system is modified. The system according to claim 11.

16. The aforementioned target measurement is a quality-related variable corresponding to the outward flow in the physical material process of the manufacturing system, and the aforementioned target measurement has a non-instantaneous and time-intensive nature due to the fact that equal sample amounts are collected at multiple points in time over a time interval, and equal sample amounts are mixed in a container measured at the end of the time interval, thereby obtaining the aforementioned target measurement. The system according to claim 11.

17. The aforementioned measurement values ​​are mixed measurement values ​​of the aggregated total amount of the sample. The aforementioned composite measurement value is a value generated at a certain point in time based on the sensor data, and is not a measurement of the aggregated total amount of the sample, but rather represents the state of the individual sample quantities at a certain point in time within the time interval. The system according to claim 16.

18. A computer program including program instructions, wherein the program instructions are executable by a processor, causing the processor to perform an operation, and the operation is: The collection of sensor data from a manufacturing system, wherein the sensor data is measured at multiple intervals shorter than the time interval of the target measurement value of the manufacturing system, and the sensor data is determined to be related to the target measurement value. Based on the aforementioned relationship, the generation of a composite target measurement at one interval of the plurality of intervals, wherein the interval is shorter than the time interval, the composite target measurement is generated using a machine learning model, the machine learning model includes a neural network trained on training data including historical sensor data and historical target measurement data, and training the machine learning model includes fitting a regression model that relates the sensor data measured at the plurality of intervals to the historical target measurement data at the time interval through unknown intermediate quality results based on a uniformly equal sample amount of the historical target measurement data over time, Automatically generate a pre-warning for the target measurement based on the composite target measurement within the interval shorter than the aforementioned time interval, A computer program that includes this.

19. One or more setting values ​​related to the manufacturing system are automatically modified based on the measurement values ​​to be synthesized, in response to the prior warnings regarding the measurement values. The computer program according to claim 18.

20. The computer program according to claim 18, wherein one or more control components related to the manufacturing system are automatically corrected based on the measurement values ​​to be synthesized in response to the prior warnings regarding the measurement values ​​to be synthesized.

Images