A cloud computing system for advanced process control and its operation method

Abstract

The present invention provides a cloud computing system for advanced process control, including a communication module, virtual machines, a data recognition and storage module, and a predictive algorithm module; wherein, the virtual machines, the data recognition and storage module, and the predictive algorithm module are all set in the cloud; the communication module is used to read on-site data from on-site sensors and transmit the data output after the operation of APC in the virtual machine to the on-site DCS; the virtual machines are used to set the internal parameters of the APC algorithm and realize the input, calculation, and output of data; the data recognition and storage module is used to identify whether the on-site data obtained by the communication module is timely and store the data that does not need to participate in the calculation temporarily, and input the timely data required for the operation of APC into APC for operation; the predictive algorithm module is used to predict on-site data and give the predicted values of on-site data. The APC of the present invention is set in the cloud, and users use the cloud APC from the on-site, which helps users save the cost of installing APC locally and helps customers lift the restriction of the binding between the DCS system and APC.

Description

Technical Field

[0001] The present invention belongs to the field of industrial control technology, and in particular relates to a cloud computing system for advanced process control and an operation method thereof. Background Art

[0002] With the continuous advancement of automation in process industries, the focus has shifted from achieving automated production to optimizing it; using advanced control algorithms to conserve raw materials, improve production conditions, reduce energy consumption, and increase yield rates, among other things. In the process industry, these advanced control algorithms are called Advanced Process Control (APC) algorithms. Examples of APC algorithms include MPC, Fuzzy Logic, and neuro-network. APC algorithms typically have one or more field inputs and one or more field outputs. APC is part of a distributed control system (DCS) and typically runs within a controller. Advanced DCS systems on the market generally support some APCs. Mature APC algorithms can be found in many DCSs; however, APCs are typically very expensive, and users want to reduce DCS costs while still using APC.

[0003] The control algorithms in DCS, including APC, are configured with a cycle during operation. They operate once in each cycle. Each operation process is divided into several steps: reading input parameters, performing algorithm calculations, and outputting the calculation results to output parameters.

[0004] Many DCS systems provide tools to help set APC internal parameters, called tuning. The tuning process involves running the APC algorithm in the field for a period of time. During this period, the APC internal parameters are set to different values to determine the process's response characteristics under different internal parameters. Based on these response characteristics, the optimal internal parameter settings can be found.

[0005] Furthermore, with the maturity of the Industrial Internet, production sites, upper layers, and even the internet are all interconnected. Running APC on remote servers or in the cloud is becoming increasingly feasible. Unlike field-based loop control algorithms, APC generally does not require continuous, low-latency field data. APC output data does not necessarily need to be quickly fed back to the control site. Running APC on the cloud and transmitting APC data via remote communication can also achieve production optimization.

[0006] CN106575282A discloses a cloud computing system and method for advanced process control. The system includes an APC control computer set locally and an APC management computer set in the cloud, thereby realizing the management of local APC in the cloud. However, the technical solution disclosed in this application still requires an APC control computer to be set locally.

[0007] Different from running APC locally, since APC does not run locally, tuning cannot be directly achieved through the local DCS. At the same time, running APC in the cloud still faces the problem of unstable network communication. When the network is unstable, data transmitted from the field may not reach APC in time, and even data loss may occur. However, APC needs to strictly calculate data according to time; at the same time, the output parameters of APC should also be transmitted to the controlled object in time. Generally, the upload speed of the network is relatively slow, making the phenomenon of data not reaching in time and being lost particularly prominent. In addition, when some field data reaches the cloud, it does not need to be immediately input into APC, but is input when needed (because APC needs to strictly calculate data according to time). At the same time, some APC output data needs to be fed back to the control field after a specific time interval. At this time, these input and output data need to be stored separately. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide a cloud computing system for advanced process control and its operation method to solve the problems in the prior art, such as the need to set an APC control computer locally, the unstable network communication when running APC in the cloud resulting in data not reaching APC in time, and the storage of some data that is not temporarily required.

[0009] To solve the above technical problems, an embodiment of the present invention provides a cloud computing system for advanced process control, which is characterized by including a communication module, a virtual machine, a data identification and storage module, and a predictive algorithm module; wherein, the virtual machine, the data identification and storage module, and the predictive algorithm module are all set in the cloud;

[0010] The communication module is used to read field data from field sensors and transmit the data output after the operation of APC in the virtual machine to the local DCS;

[0011] The virtual machine automatically configures the same operating system according to the local DCS system, installs the software required for the operation of APC, and completely copies the interface for docking data with APC; the virtual machine is used to set the internal parameters of the APC algorithm and realize the input, calculation, and output of data;

[0012] The data identification and storage module is used to identify whether the field data obtained by the communication module is timely, store data that is temporarily not required for calculation, and input the timely data required for APC operation into the APC for calculation;

[0013] The predictive algorithm module is used to predict on-site data when the data identification and storage module detects delayed network data transmission or packet loss, providing a predicted value for the on-site data. This value is then input into the APC for computation. In the present invention, the virtual machine automatically configures the same operating system as the on-site DCS system, providing a cloud-based execution environment identical to that of the on-site system. Preferably, this execution environment is Microsoft Windows or Linux.

[0014] Furthermore, the communication module includes a data interface and a communication line for reading data from field sensors. The main function of the communication module in the present invention is to read field data through field sensors and transmit the data output by the APC to the field DCS.

[0015] Furthermore, the data identification and storage module is used to periodically detect whether the communication module has field data input and the time information on the timestamp of the input data; if the time in the input data is consistent with the APC software setting, the data uploaded from the field will be input into the APC software for calculation; if there is no field data input within a calculation cycle, the predictive algorithm module will use the prediction model to perform predictive calculations based on the previous input data to obtain a predicted value of the field data, and input the predicted value into the APC for calculation, thereby obtaining the output data of the APC.

[0016] Furthermore, the data identification and storage module is used to store data that does not need to be involved in the calculation temporarily: when some data does not need to be calculated by APC immediately, if the time in the input data is earlier than the calculation time set in APC, the data will be stored in the data identification and storage module; when the predetermined time is reached, the stored data will be input into APC for calculation.

[0017] Furthermore, the cloud computing system also includes a virtual firewall, which is used to ensure cloud security and is placed in front of the virtual machine, data identification and storage module, and predictive algorithm module.

[0018] An embodiment of the present invention further provides a method for operating a cloud computing system for advanced process control, characterized by comprising the following steps:

[0019] (1) The user installs and operates the DCS system on site;

[0020] (2) Build virtual machines, data recognition and storage modules, and predictive algorithm modules in the cloud; connect the data between the cloud and the site through a communication module;

[0021] (3) Obtain the internal parameters of the APC according to the site;

[0022] (4) The virtual machine in the cloud automatically configures the corresponding operating system according to the on-site DCS system, installs the adapted APC software, and configures the internal parameters according to the internal parameters of the APC obtained in step (3);

[0023] (5) The data recognition and storage module recognizes, stores, and transmits the data input by the communication module;

[0024] (6) Run the APC algorithm in the cloud and return the operation results to the DCS at the user site to achieve advanced process control on the cloud.

[0025] Further, the obtaining of the internal parameters of the APC in step (3) can be implemented in one of the following three implementation methods according to the site conditions:

[0026] a. Temporarily run the APC in the on-site DCS environment to determine the internal parameter values, and then write these parameter values into the cloud APC;

[0027] b. Temporarily build the same architecture as the cloud in the non-DCS environment on-site, obtain the internal parameter values, and then write these parameter values into the cloud APC;

[0028] c. When the Internet communication effect is good, the internal parameter values can be directly determined in the cloud.

[0029] Among them, the process of determining whether the Internet communication is good in method c is as follows: Transmit the data of the on-site DCS system to the cloud. Before running the data in the DCS system, the APC checks the time information in the timestamp of the input data. If the time recorded in the timestamp is the same as the time preset by the system, it means that the network communication is good, and at this time, the internal parameter values can be determined in the cloud.

[0030] Further, the process of the data recognition and storage module processing the data input by the communication module in step (5) specifically includes the following:

[0031] (5-1) The recognition process of the data recognition and storage module

[0032] (5-1-1) During the operation of the APC software, the data recognition and storage module regularly detects whether there is on-site data input by the communication module and the time information on the timestamp of the input data;

[0033] (5-1-2) If the time in the input data is consistent with the APC software setting, the data uploaded from the site will be input into the APC software for calculation;

[0034] (5-1-3) If there is no field data input during a calculation cycle, the predictive algorithm module will use the prediction model to perform predictive calculations based on the previous input data to obtain a predicted value of the field data, and input the predicted value into the APC for calculation to obtain the APC output data;

[0035] (5-2) Storage process of the data identification and storage module

[0036] (5-2-1) When some data does not need to be immediately processed by APC, if the time in the input data is earlier than the calculation time set in APC, the data will be stored in the data recognition and storage module;

[0037] (5-2-2) When the scheduled time is reached, the stored data is input into the APC for calculation.

[0038] Preferably, the APC algorithm module in the virtual machine can be optimized and further improved according to market needs to adapt to different on-site DCSs.

[0039] The beneficial effects of the above technical solution of the present invention are as follows:

[0040] The present invention sets the APC in the cloud and allows users to use the cloud APC on site, which helps users save the cost of installing the APC locally and can help customers remove the restrictions on the binding of the DCS system and APC (that is, the DCS supplier actually used by the user on site can be different from the supplier of the APC running in the cloud).

[0041] The cloud computing system of the present invention includes a data identification and storage module and a predictive algorithm module; the data identification and storage module identifies whether field data is provided in a timely manner. When there is no field data within the operating cycle, the predictive algorithm module provides a field prediction value, thereby solving the problem of untimely data transmission that may be encountered when the APC is set up in the cloud; at the same time, the data identification and storage module can also be used to store data that does not require immediate APC calculation, and input it into the APC for calculation when calculation is required.

[0042] In the present invention, since the APC is set up in the cloud, it is convenient to quickly update and optimize the algorithm in the APC. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 FIG. 1 is a block diagram of an example cloud computing system in communication with several users according to an embodiment of the present invention.

[0044] Figure 2Flow chart of steps in the operation method of the cloud computing system for advanced process control of the present invention.

[0045] Figure 3 Block diagram of the communication between the cloud computing system of the present invention and User 1 in the embodiment.

[0046] Explanation of reference numerals:

[0047] 100, Cloud; 101, Virtual machine; 102, Data identification and storage module; 103, Predictive algorithm module; 110, Communication module; 120, User 1; 121, Liquid level sensor; 122, Weighing sensor; 123, Infrared sensor; 124, Field DCS system; 125, Water valve; 126, Drug addition valve; 127, Alarm; 130, User 2; 140, User 3; 150, Internet. Detailed implementation manners

[0048] The disclosed embodiments are described with reference to the accompanying drawings, in which like reference numerals are used throughout the drawings to designate similar or equivalent elements. The drawings are not drawn to scale and are provided only to illustrate certain disclosed aspects. Several disclosed aspects are described below with reference to example applications for illustration. It should be understood that numerous specific details, relationships, and methods are set forth to provide a complete understanding of the disclosed embodiments.

[0049] However, those of ordinary skill in the relevant art will readily recognize that the subject matter disclosed herein may be practiced without one or more of the specific details or using other methods. In other instances, well-known structures or operations are not shown in detail to avoid obscuring certain aspects. The present disclosure is not limited by the order of the actions or events illustrated, as some actions may occur in a different order and / or concurrently with other actions or events. Additionally, not all of the illustrated actions or events are required to implement the method according to the disclosed embodiments.

[0050] In the description of the present invention, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0051] Embodiments of the present invention provide a cloud computing system for advanced process control, including a communication module 110, a virtual machine 101, a data identification and storage module 102, and a predictive algorithm module 103. Among them, the virtual machine 101, the data identification and storage module 102, and the predictive algorithm module 103 are all set in the cloud 100. The communication module 110 is used to read field data from field sensors and transmit the data output after the operation of APC in the virtual machine 101 to the DCS on site. The virtual machine 101 automatically configures the same operating system according to the on-site DCS system and installs the software required for the operation of APC, and completely replicates the interface for docking data with APC. The virtual machine 101 is used to set the internal parameters of the APC algorithm to realize the input, calculation, and output of data. The data identification and storage module 102 is used to identify whether the field data obtained by the communication module 110 is timely, store the data that does not need to participate in the calculation temporarily, and input the timely data required for the operation of APC into APC for operation. The predictive algorithm module 103 is used to predict the field data when the data identification and storage module 102 detects that the network data transmission is not timely or data packets are lost, give the predicted value of the field data, and input the predicted value of the field data into APC for operation.

[0052] Figure 1 The block diagram of an example cloud computing system including several users including User 1 120, User 2 130, and User 3 140 is illustrated. Each user can be a separate company or entity that produces goods or services. Each user's site has a DCS system, and the DCS system on site may include advanced process control (APC). With or without advanced process control (APC), the actual DCS supplier used at the user's site can be different from the supplier of the APC running in the cloud in the present invention. As Figure 1 shown, the cloud computing system includes a communication module 110, a virtual machine 101, a data identification and storage module 102, and a predictive algorithm module 103. The communication module 110 is connected to the user's on-site DCS system and field sensors through a data interface and a communication line, and the communication module 110 transmits data to and from the cloud through the Internet.

[0053] As Figure 3 shown, embodiments of the present invention also provide a method for operating a cloud computing system for advanced process control, including the following processes:

[0054] (1) The user installs and runs the DCS system on site.

[0055] (2) Build a virtual machine 101, a data identification and storage module 102, and a predictive algorithm module 103 in the cloud; and connect the data between the cloud and the site through the communication module 110.

[0056] (3) Obtain the internal parameters of the APC according to the site.

[0057] (4) The cloud virtual machine 101 automatically configures the corresponding operating system according to the on-site DCS system, installs the corresponding APC software, and configures the internal parameters according to the APC internal parameters obtained in step (3).

[0058] (5) The data identification and storage module 102 identifies, stores and transmits the data input by the communication module 110.

[0059] The data identification and storage module 102 processes the data input by the communication module, specifically including the following:

[0060] (5-1) Identification process of the data identification and storage module 102

[0061] (5-1-1) During the operation of the APC software, the data identification and storage module 102 periodically checks whether the communication module 110 has field data input and the time information on the timestamp of the input data;

[0062] (5-1-2) If the time in the input data is consistent with the APC software setting, the data uploaded from the site will be input into the APC software for calculation;

[0063] (5-1-3) If no field data is input during a calculation cycle, the predictive algorithm module 103 utilizes the prediction model to perform predictive calculations based on the previous input data, deriving a predicted value for the field data, and inputting this predicted value into the APC for calculation, thereby obtaining the APC output data. In the present invention, the predictive algorithm in the predictive algorithm module 103 may employ conventional existing algorithms, such as using the most recent field data, using pre-set values, or performing an estimate based on multiple preceding values by incorporating a mathematical formula. The predictive algorithm may also be customized based on the specific application scenario.

[0064] (5-2) Storage process of the data identification and storage module 102

[0065] (5-2-1) When some data does not need to be immediately processed by the APC, if the time in the input data is earlier than the calculation time set in the APC, the data will be stored in the data identification and storage module 102;

[0066] (5-2-2) When the scheduled time is reached, the stored data is input into the APC for calculation.

[0067] (6) Run the APC algorithm in the cloud and return the calculation results to the user's on-site DCS to achieve advanced process control in the cloud.

[0068] like Figure 3The figure shows the application of a cloud computing system for advanced process control at user 120. In this embodiment, user 120 is a water treatment company equipped with on-site sensors such as a level sensor 121 for detecting wastewater levels, a weighing sensor 122 for measuring the weight of water treatment additives, and an infrared sensor 123 for monitoring the proximity of personnel to the wastewater treatment tank. The company is also equipped with a DCS system 124, which is connected to a water valve 125, a drug addition valve 126, and an alarm 127. When using the cloud computing system of the present invention, a virtual machine 101, a data recognition and storage module 102, and a predictive algorithm module 103 are constructed on the cloud for user 1. These on-site sensors, such as the level sensor 121 for detecting wastewater levels, the weighing sensor 122, and the infrared sensor 123 for monitoring the proximity of personnel to the wastewater treatment tank, as well as the on-site DCS system 124, are connected to a communication module 110. This communication module 110 is then connected to the cloud 100 via the internet 150. According to the on-site conditions, adjustment is performed (APC internal parameters are obtained), and the corresponding operating system is automatically configured in the virtual machine 101 of user 1 built on the cloud 100 according to the on-site DCS system 124, the corresponding APC software is installed, and the APC internal parameters are configured; the cloud APC is run, and the data recognition and storage module 102 recognizes the data input by the communication module 110. If the time in the input data is consistent with the APC software setting, the data uploaded from the site is input into the APC software for calculation; if no on-site data is input within an operation cycle; the predictive algorithm module 103 obtains a predicted value based on the data input in the early stage, and inputs the predicted value into the APC for calculation. The APC outputs the calculation result to the DCS system 124 of user 1 through the communication module. The DCS system 124 controls the on-site water valve 125, drug addition valve 126 and alarm 127 according to the received result data.

[0069] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A cloud computing system for advanced process control, characterized in that It includes a communication module, a virtual machine, a data recognition and storage module, and a predictive algorithm module; among them, the virtual machine, the data recognition and storage module, and the predictive algorithm module are all set in the cloud; The communication module is used to read on-site data from on-site sensors and transmit the data output after the operation of the virtual machine APC (Advanced Process Control) algorithm to the on-site DCS system; The virtual machine automatically configures the same operating system according to the on-site DCS system and installs the software required for the operation of the APC algorithm, and completely replicates the interface for docking data with the APC algorithm; the virtual machine is used to set the internal parameters of the APC algorithm to realize the input, calculation, and output of data; The data recognition and storage module is used to identify whether the on-site data obtained by the communication module is timely, store the data that does not need to participate in the calculation temporarily, and input the timely data required for the operation of the APC algorithm into the APC algorithm for operation; The predictive algorithm module is used to predict on-site data when the data recognition and storage module detects that network data transmission is not timely or data packets are lost, give the predicted value of on-site data, and input the predicted value of on-site data into the APC algorithm for operation.

2. The cloud computing system for advanced process control according to claim 1, wherein The communication module includes a data interface for reading data from on-site sensors and a communication line.

3. The cloud computing system for advanced process control according to claim 1, wherein The data recognition and storage module is used to regularly detect whether there is on-site data input by the communication module and the time information on the timestamp of the input data; if the time in the input data is the same as that set by the APC algorithm, the data uploaded from the site will be input into the APC algorithm for operation; if there is no on-site data input within one operation cycle, the predictive algorithm module will use the prediction model to perform predictive calculations based on the previous input data, obtain a predicted value of on-site data, and input the predicted value into the APC algorithm for operation, so as to obtain the output data of the APC algorithm.

4. A cloud computing system for advanced process control according to claim 1, characterized in that, The data recognition and storage module is used to store the data that does not need to participate in the calculation temporarily: when some data does not need to be immediately operated by the APC algorithm, if the time in the input data is earlier than the operation time set in the APC algorithm, the data will be stored in the data recognition and storage module; when the predetermined time arrives, the stored data will be input into the APC algorithm for operation.

5. A cloud computing system for advanced process control according to claim 1, wherein, It also includes a virtual firewall, which is used to ensure the security of the cloud and is placed in front of the virtual machine, the data recognition and storage module, and the predictive algorithm module.

6. A method for operating a cloud computing system for advanced process control according to claim 1, characterized in that, It includes the following processes: (1) The user installs and runs the on-site DCS system on-site; (2) Build the virtual machine, data recognition and storage module, and predictive algorithm module in the cloud; and connect the data between the cloud and the site through the communication module; (3) Obtain the internal parameters of the APC algorithm according to the on-site DCS system; (4) The virtual machine in the cloud automatically configures the corresponding operating system according to the on-site DCS system, installs the adapted APC algorithm, and configures the internal parameters according to the internal parameters of the APC algorithm obtained in step (3); (5) The data recognition and storage module identifies, stores, and transmits the data input by the communication module; (6) Run the APC algorithm in the cloud and return the operation results to the user's on-site DCS system to achieve advanced process control in the cloud.

7. The operating method of a cloud computing system for advanced process control according to claim 6, characterized in that, The acquisition of the internal parameters of the APC algorithm in step (3) is implemented in one of the following three ways according to the on-site situation: a. Temporarily run the APC algorithm in the on-site DCS system, determine the internal parameter values, and then write these parameter values into the cloud APC algorithm; b. Temporarily build the same architecture as the cloud in the on-site non-DCS system. After obtaining the internal parameter values, write these parameter values into the cloud APC algorithm; c. When the Internet communication meets the preset conditions, directly determine the internal parameter values in the cloud.

8. The operating method of a cloud computing system for advanced process control according to claim 7, characterized in that, The process of determining whether the Internet communication meets the preset conditions in method c is as follows: Transmit the data of the on-site DCS system to the cloud. Before the APC algorithm runs each data in the on-site DCS system, it checks the time stamp in the data. If the time recorded in the time stamp is the same as the time preset by the system, it means that the network communication meets the preset conditions. At this time, determine the internal parameter values in the cloud.

9. The operating method according to the claims of a cloud computing system for advanced process control as claimed in claim 6, characterized in that, In the process of step (5), the data recognition and storage module processes the data input by the communication module, which specifically includes the following: (5-1) The recognition process of the data recognition and storage module (5-1-1) During the operation of the APC algorithm, the data recognition and storage module regularly detects whether the communication module has on-site data input and the time information on the time stamp of the input data; (5-1-2) If the time in the input data is the same as that set by the APC algorithm, the data uploaded from the on-site will be input into the APC algorithm for operation; (5-1-3) If there is no on-site data input within one operation cycle, the predictive algorithm module will use the prediction model to perform predictive calculations based on the previous input data, obtain a predicted value of the on-site data, and input this predicted value into the APC algorithm for operation, so as to obtain the output data of the APC algorithm; (5-2) The storage process of the data recognition and storage module (5-2-1) When some data does not need to be immediately operated by the APC algorithm, if the time in the input data is earlier than the operation time set in the APC algorithm, this data will be stored in the data recognition and storage module; (5-2-2) When the predetermined time arrives, the stored data will be input into the APC algorithm for operation.

10. The method for operating according to a claim of a cloud computing system for advanced process control according to claim 6, characterized in that, The APC algorithm module in the virtual machine can be optimized.

Images