Predictive troubleshooting for abnormal plant operations

Abstract

The present invention is entitled "Predictive Troubleshooting for Abnormal Plant Operations". A system and method are provided for recording and subsequently displaying comments containing suggested actions to be taken in response to abnormal conditions that occur during process operations. The operator can rank the comments based on their level of success in correcting the abnormal conditions, and the highest ranked actions are displayed first.

Description

Technical Field

[0001] The field of the invention is industrial automation, and more particularly systems and processes for operation of batch or sequential operations for predicted time-based control in anticipation of or reaction to abnormal conditions. Background Art

[0002] Many types of industrial processes involve sequential operations during the manufacture or production of a product. Common examples are found in the food and beverage, specialty chemicals, and pharmaceutical industries, where discrete steps are often performed in series on a batch of input materials to produce a batch of output products. Sequential operations are also often performed in continuous process industries such as energy production, where multiple pieces of equipment are periodically accessed through a sequence of operations to start, stop, or clean the equipment or to switch between different pieces of equipment.

[0003] Recently, progress has been made in providing rapid two-way communications between an operator and other team members and providing operational information in the form of messages to the operator. In such communications, a message from a processing unit is recorded when a signal is received from one or more sensors. The processing unit includes a processor having a memory for storing the signal and recording the signal in the memory. The processor includes a memory for storing a program for running the processing unit and includes control information about the operational limits of the signal. When the signal received from the sensor is outside the operational limits of the program, the processor generates a message. The method includes sending the generated message to an operator station and prompting the operator to respond. The generated message may send a link to a menu of possibly pre-programmed responses for the operator to select from, or may allow the operator to enter a response. The operator's response is recorded for future reference. The method allows for input of signal data, generated graphics, and additional information stored and available to other operators.

[0004] Currently, there is no method to automatically predict abnormal situations in batch processing before they occur so that they can be prevented from occurring or the appropriate personnel can quickly react and correct the abnormal situation. In batch processing or other types of processing, the way such situations are handled and the actions required to troubleshoot and repair the abnormal situation is that they are recorded on paper by the operator. This data is not available for easy analysis and learning to prevent abnormal situations from occurring in the future or to troubleshoot problems in the batch more quickly, thereby reducing downtime and batch throughput and ensuring batch quality. Capturing the operator's comments and their recommended recovery actions in an electronic format ensures data integrity compliance, allows easy access and review of valuable data to improve processes, and can be used for data and batch analysis to predict abnormal situations and recommend correct actions, thereby reducing the time required to troubleshoot abnormal situations and reducing the training required for inexperienced operators. The same principles can be applied to continuous manufacturing. Summary of the invention

[0005] The present invention provides a fast two-way communication between operators and other team members, and provides operational information to operators of abnormal operating conditions in the form of sent messages. The method records messages from a processing unit when a signal is received from one or more sensors. The processing unit includes a processor having a memory for storing the signal and recording the signal in the memory. The processor includes a memory for storing a program for running the processing unit, and includes control information about the operating limits of the signal. When the signal received from the sensor is outside the operating limit of the program, the processor generates a message. There are multiple abnormal conditions that the system can detect. Delays can be detected by comparing the cycle time of the current stage with the cycle time recorded in the reference batch run. So far, delays have been detected and displayed on the timeline of the current operation. Another abnormal condition may be an exceedance. Key performance indicator parameters on units and recipes can be configured by engineers and monitored at runtime, and each key performance indicator parameter has a range set in the master recipe. When the parameter exceeds the range, the system will detect the abnormal condition and display an indication on the unit timeline, which can be monitored on a tablet, computer monitor or other output device. Another indication of an abnormal condition may be an alarm displayed on the unit timeline. When any of these abnormal conditions are detected, the condition will be visualized to the operator and a new context menu will be made available for response or comment. When the operator successfully troubleshoots the abnormal condition and returns to normal operation, a menu will be displayed and the operator can select a comment from a stage on the process graphic, unit timeline or other input screen. The system will provide information that will capture the batch identification of the batch being run and other information, including the location and assets or units involved in the abnormal condition that occurred. The operator can select a problem category such as delay, out of range, maintenance, equipment or other problems. The system can then query the event log and return a list of previously entered comments, including recommended actions. In addition, the comments can be provided in the order of those actions that have historically been considered the highest recommended, and the ability to expand the list in the relevant order and view the entire list. The operator can then select a comment from the historical list and / or they can enter their new comment into text by typing or voice input that can then be converted to text. The system then logs the new type of event (comment event) to the event log maintained on the server. The event log does capture all identifying information, including the batch ID, location or asset / unit, specific parameters involved, problem category, comment text, recommended actions, operator username, date and time. Operators can enter some "like" or "dislike" comments, which the system uses to increment or decrement the ranking of the comment relative to other comments. In the future, when comments are displayed, the algorithm will display the most relevant recommended actions based on a combination of ranking, problem category, recipe and location.For example, the first three suggested actions may be presented, although the system may be modified to display a different number of suggested actions. The generated message may send a link to a menu of possible pre-programmed responses for the operator to select from, or may allow the operator to enter a response. The operator's response is recorded for future reference. The method allows for input of signal data, generated graphics, and additional information to be stored and available to other operators.

[0006] In another embodiment, the present invention includes a supplement to a distributed control system for recording a message and transmitting the message to an operator when a processing unit encounters an abnormal condition, and recording a response from an operator and transmitting the response. The device includes a sensor that generates a processing signal, and the processing signal indicates a processing condition, such as, for example, temperature. The device also includes a processor, which includes a memory for storing a control program to operate the processing unit, wherein the processor includes a storage device for storing signals and creates a signal record. The control program (also referred to as a recipe) includes processing limits, and a message is generated when the processing signal exceeds the limit. The generated message includes information about the process, the recipe, and the type of signal generated by the sensor. The device includes a communication device for sending messages to an operator and receiving comments from the operator that constitute a response. The communication may include a signal data stream and output information in the form of a graph or other convenient way to display the results.

[0007] Other objects, embodiments and details of the present invention can be obtained from the following drawings and detailed description of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 An industrial process control and automation system is shown.

[0009] Figure 2 A flow chart showing the process is shown.

[0010] Figure 3 Shows the sequence of steps taken when an abnormal situation occurs in a batch operation.

[0011] Figure 4 Shows the steps that can be taken when batch cycle time is delayed. DETAILED DESCRIPTION

[0012] Communications are important in today's industrial processing plants. Rapid transmission of information and records is needed to leverage information against similar situations in the past, thereby continually providing greater responsiveness in the operation of industrial processes. Currently, industrial plants rely on telephone communications or other electronic communications to disclose abnormal operating conditions. There is a need to improve these communications and provide more information. Such improvements reduce losses due to product loss or downtime.

[0013] The present invention provides for more immediate communication, as well as providing more complete information to the controller or to the operator to provide a solution to the situation encountered.

[0014] Figure 1 An exemplary industrial automation system 100 according to the present disclosure is shown. Figure 1 As shown, system 100 includes various components that facilitate the production or processing of at least one product or other material. For example, system 100 is used herein to facilitate the control of components in one or more plant buildings 101a to 101n. Each plant building 101a to 101n represents one or more processing facilities (or one or more parts thereof), such as one or more manufacturing facilities for producing at least one product or other material. Generally speaking, each plant building 101a to 101n can implement one or more processes and can be referred to as a process system individually or collectively. A process system generally represents any system or part thereof that is configured to process one or more products or other materials in some manner.

[0015] exist Figure 1 In the embodiment of the present invention, the system 100 is implemented using the Purdue model of process control. In the Purdue model, "level 0" may include one or more sensors 102a and one or more actuators 102b. Sensors 102a and actuators 102b represent components in a process system that can perform any of a variety of functions. For example, sensor 102a can measure a variety of characteristics in a process system, such as temperature, pressure, or flow. In addition, actuator 102b can change a variety of characteristics in a process system. Sensors 102a and actuators 102b may represent any other or additional components in any suitable process system. Each sensor in sensor 102a includes any suitable structure for measuring one or more characteristics in a process system. Each actuator in actuator 102b includes any suitable structure for operating or affecting one or more conditions in a process system. Sensors and actuators may generally be referred to as field devices.

[0016] At least one network 104 is coupled to the sensor 102a and the actuator 102b. The network 104 facilitates interaction with the sensor 102a and the actuator 102b. For example, the network 104 may transmit measurement data from the sensor 102a and provide control signals to the actuator 102b. The network 104 may represent any suitable network or combination of networks. As a specific example, the network 104 may represent an Ethernet network, an electrical signal network (such as a HART or Foundation Fieldbus network), a pneumatic control signal network, or any other or additional type of network.

[0017] In the Purdue model, "Level 1" may include one or more controllers 106 coupled to the network 104. Among other things, each controller 106 may use measurements from one or more sensors 102a to control the operation of one or more actuators 102b. For example, the controller 106 may receive measurement data from one or more sensors 102a and use the measurement data to generate control signals for one or more actuators 102b. Multiple controllers 106 may also operate in a redundant configuration, such as when one controller 106 operates as a primary controller and another controller 106 operates as a backup controller (which is synchronized with the primary controller and can take over the primary controller in the event of a failure of the primary controller). Each controller 106 includes any suitable structure for interacting with one or more sensors 102a and controlling one or more actuators 102b. Each controller 106 may, for example, represent a multivariable controller, such as a robust multivariable predictive control technology (RMPCT) controller or other types of controllers that implement model predictive control (MPC) or other advanced predictive control (APC). As a specific example, each controller 106 may represent a computing device running a real-time operating system.

[0018] Two networks 108 are coupled to the controller 106. The networks 108 facilitate interaction with the controller 106, such as by transmitting data to and from the controller 106. The networks 108 may represent any suitable network or combination of networks. As a specific example, the networks 108 may represent a pair of Ethernet networks or a pair of redundant Ethernet networks, such as a Fault Tolerant Ethernet (FTE) network from HONEYWELL INTERNATIONAL INC.

[0019] At least one switch / firewall 110 couples network 108 to two networks 112. Switch / firewall 110 can transfer traffic from one network to another network. Switch / firewall 110 can also prevent traffic on one network from reaching another network. Switch / firewall 110 includes any suitable structure for providing communication between networks, such as a HONEYWELL CONTROL FIREWALL (CF9) device. Network 112 can represent any suitable network, such as a pair of Ethernet networks or an FTE network.

[0020] In the Purdue model, "Level 2" may include one or more machine-level controllers 114 coupled to the network 112. The machine-level controllers 114 perform various functions to support the operation and control of the controller 106, sensors 102a, and actuators 102b that may be associated with a particular industrial device, such as a boiler or other machine. For example, the machine-level controller 114 may record information collected or generated by the controller 106, such as measurement data from the sensor 102a or control signals for the actuator 102b. The machine-level controller 114 may also execute an application that controls the operation of the controller 106, thereby controlling the operation of the actuator 102b. In addition, the machine-level controller 114 may provide secure access to the controller 106. Each of the machine-level controllers 114 includes any suitable structure for providing access to, control of, or operations related to a machine or other individual device. Each of the machine-level controllers 114 may, for example, represent a server computing device running a MICROSOFT WINDOWS operating system. Although not shown, different machine-level controllers 114 may be used to control different devices in the process system (where each device is associated with one or more controllers 106 , sensors 102a , and actuators 102b ).

[0021] One or more operator stations 116 are coupled to the network 112. The operator stations 116 represent computing devices or communication devices that provide user access to the machine-level controller 114, which in turn may provide user access to the controller 106 (and possibly the sensor 102a and actuator 102b). As a specific example, the operator station 116 may allow a user to view the operation history of the sensor 102a and actuator 102b using information collected by the controller 106 and / or the machine-level controller 114. The operator station 116 may also allow a user to adjust the operation of the sensor 102a, actuator 102b, controller 106, or machine-level controller 114. In addition, the operator station 116 may receive and display warnings, alerts, or other messages or displays generated by the controller 106 or the machine-level controller 114. Each of the operator stations 116 includes any suitable structure for supporting user access and control of one or more components in the system 100. Each of the operator stations 116 may, for example, represent a computing device running a MICROSOFT WINDOWS operating system.

[0022] At least one router / firewall 118 couples network 112 to two networks 120. Router / firewall 118 includes any suitable structure for providing communication between networks, such as a security router or a combination router / firewall. Network 120 may represent any suitable network, such as a pair of Ethernet networks or an FTE network.

[0023] In the Purdue model, "Level 3" may include one or more unit-level controllers 122 coupled to the network 120. Each unit-level controller 122 is typically associated with a unit in the process system, which represents a collection of different machines that operate together to implement at least a portion of the process. The unit-level controller 122 performs various functions to support the operation and control of components in the lower level. For example, the unit-level controller 122 may record information collected or generated by components in the lower level, execute applications that control components in the lower level, and provide secure access to components in the lower level. Each of the unit-level controllers 122 includes any suitable structure for providing access to, control of, or operations related to one or more machines or other devices in the processing unit. Each of the unit-level controllers 122 may, for example, represent a server computing device running a MICROSOFT WINDOWS operating system. Although not shown, different unit-level controllers 122 may be used to control different units in the process system (where each unit is associated with one or more machine-level controllers 114, controllers 106, sensors 102a, and actuators 102b).

[0024] Access to the unit-level controller 122 may be provided by one or more operator stations 124. Each of the operator stations 124 includes any suitable structure for supporting user access and control of one or more components in the system 100. Each of the operator stations 124 may represent, for example, a computing device running a MICROSOFT WINDOWS operating system.

[0025] At least one router / firewall 126 couples network 120 to two networks 128. Router / firewall 126 includes any suitable structure for providing communication between networks, such as a security router or a combination router / firewall. Network 128 may represent any suitable network, such as a pair of Ethernet networks or an FTE network.

[0026] In the Purdue model, "Level 4" may include one or more plant-level controllers 130 coupled to a network 128. Each plant-level controller 130 is typically associated with one of the plants 101a to 101n, which may include one or more processing units implementing the same, similar, or different processes. The plant-level controller 130 performs various functions to support the operation and control of components in the lower levels. As a specific example, the plant-level controller 130 may execute one or more manufacturing execution system (MES) applications, scheduling applications, or other or additional plant or process control applications. Each of the plant-level controllers 130 includes any suitable structure for providing access to, control of, or operations related to one or more processing units in a processing plant. Each of the plant-level controllers 130 may, for example, represent a server computing device running a MICROSOFT WINDOWS operating system.

[0027] Access to the plant-level controller 130 may be provided by one or more operator stations 132. Each of the operator stations 132 includes any suitable structure for supporting user access and control of one or more components in the system 100. Each of the operator stations 132 may represent, for example, a computing device running a MICROSOFT WINDOWS operating system.

[0028] At least one router / firewall 134 couples network 128 to one or more networks 136. Router / firewall 134 includes any suitable structure for providing communication between networks, such as a security router or a combination router / firewall. Network 136 may represent any suitable network, such as a full enterprise Ethernet or other network, or all or a portion of a larger network such as the Internet.

[0029] In the Purdue model, "Level 5" may include one or more enterprise-level controllers 138 coupled to a network 136. Each enterprise-level controller 138 is typically capable of performing planning operations for multiple plants 101a to 101n and controlling various aspects of the plants 101a to 101n. The enterprise-level controller 138 may also perform various functions to support the operation and control of components in the plants 101a to 101n. As a specific example, the enterprise-level controller 138 may execute one or more order processing applications, enterprise resource planning (ERP) applications, advanced planning and scheduling (APS) applications, or any other or additional enterprise control applications. Each of the enterprise-level controllers 138 includes any suitable structure for providing access to, control of, or control-related operations on one or more plants. Each of the enterprise-level controllers 138 may, for example, represent a server computing device running a MICROSOFT WINDOWS operating system. In this document, the term "enterprise" refers to an organization with one or more plants or other processing facilities to be managed. Note that if a single plant 101a is to be managed, the functionality of the enterprise-level controller 138 may be incorporated into the plant-level controller 130 .

[0030] Access to the enterprise-level controller 138 may be provided by one or more operator stations 140. Each of the operator stations 140 includes any suitable structure for supporting user access and control of one or more components in the system 100. Each of the operator stations 140 may represent, for example, a computing device running a MICROSOFT WINDOWS operating system.

[0031] Each level of the Purdue model may include other components, such as one or more databases. The database associated with each level may store any suitable information associated with that level or one or more other levels of the system 100. For example, a historical database 141 may be coupled to the network 136. The historical database 141 may represent a component that stores various information about the system 100. The historical database 141 may, for example, store information used during production scheduling and optimization. The historical database 141 represents any suitable structure for storing information and facilitating information retrieval. Although shown as a single centralized component coupled to the network 136, the historical database 141 may be located elsewhere in the system 100, or multiple historical databases may be distributed at different locations in the system 100.

[0032] In certain embodiments, Figure 1The various controllers and operator stations in may represent computing devices. For example, each of the controllers may include one or more processing devices 142 and one or more memories 144 for storing instructions and data used, generated, or collected by the processing device 142. Each of the controllers may also include at least one network interface 146, such as one or more Ethernet interfaces or a wireless transceiver. In addition, each of the operator stations may include one or more processing devices 148 and one or more memories 150 for storing instructions and data used, generated, or collected by the processing device 148. Each of the operator stations may also include at least one network interface 152, such as one or more Ethernet interfaces or a wireless transceiver.

[0033] Currently, any analysis of past anomalies using data to reduce batch cycle time is a manual process that requires additional analysis tools that require manual configuration and increase system cost. The present disclosure will provide that the system will automatically collect relevant data from the operator when a delay or other anomaly occurs and visualize a portion of the batch process and any related equipment with past anomalies and use that data to predict future problems or provide guidance to the operator to correct the problem without manual troubleshooting that may be time consuming. It will also provide guidance to the operator to suggest the best path for the batch based on past data. Provisions are provided for generating additional events and data that can be used to generate batch analysis, which can then be analyzed.

[0034] The system and its implementation enables operators to prevent potential problems before they cause delays in batch processing, or enables them to gain information to quickly troubleshoot the problem and get batch production back on track, thereby reducing overall batch cycle time.

[0035] An important aspect of the present invention is the communication between the field service personnel and the operator at the operator station 116. The field service personnel check the routine operation of the processing unit on site. The operator is located at the operation center (rather than at the plant or even remotely located) to monitor the information from the processing unit. When an abnormal condition occurs, rapid communication between the operator and the field service personnel is important to reduce downtime and return the process to normal operating conditions.

[0036] By capturing operational signals indicating an abnormal condition, the operator can send a copy of the signal and enable the field service personnel to return the process to normal operating conditions by providing them with supporting information and a message indicating the source of the problem.

[0037] Likewise, the field service personnel may transmit photos or other information regarding messages that have been saved from previous abnormal conditions to an operator, who may evaluate the information from the field service personnel.

[0038] Additionally, the present invention provides important communications where an operator can notify field service personnel of abnormal conditions and can send signal data or other information. Field service personnel can check to see not only if there is a change in the operation of the processing unit, but also if there is a fault signal due to a sensor failure, or a change in the signal due to an actuator failure or other faulty equipment.

[0039] In the present invention, the operating unit includes a sensor and an actuator, wherein information is transmitted from the sensor to the controller, and the controller sends a response to the actuator for the process. When the controller receives an abnormal condition, the present invention provides a fast response. Figure 2 , a process 200 is shown. Process 210 is monitored by an operator. The process has a sensor that generates a signal indicating the operating condition of a processing unit 160. A processing unit 160 is any operating unit in a plant that produces a product or an intermediate product and is monitored by a sensor attached to the processing unit 160 and has an actuator for modifying the condition in the processing unit 160. Examples include a chemical reactor, a separation unit, or even a part of an assembly line, such as a process of filling a bottle or a can. The signal is received by a processor, wherein the signal from the sensor on the processing unit 160 is stored in a memory, and a processor or controller 106 associated with the processing unit 160 includes the memory. The processor also includes a memory for storing a control recipe for operating the processing unit 160. A control recipe is a program designed for operating the processing unit 160. The control recipe includes the operating limits of the signal. When the processor detects an abnormal condition 220 or a signal outside the operating limits, the system generates a message 230 indicating that the signal is abnormal or outside the operating limits as specified by the recipe. The generated message can be sent to a display of the operating unit. The message may generate a prompt for the operator to respond to the message. The generated message includes information about the process, the control recipe, and the type of signal generated by the sensor. The operator then selects a response to the message 240.

[0040] The message may be a preprogrammed response that the operator enters or selects from a menu or allows the system to select a default response. The menu presents a list of options 250 based on the type of processing unit 160 and sensor 102a. The options are sorted according to relevance, severity, historical actions, or some combination of appropriate weights with abnormal conditions to provide guidance to the operator. When a process has been recorded as deviating from the limits set in the process recipe, a menu is generated from the past operating conditions of the process. This provides the operator with a quick list of current abnormal conditions and causes. Relevance is based on the severity of the signal and the frequency with which similar signals have been received in the past. For example, for a heating mixer, the message may be "mixer heating outside the limits", or "temperature outside the mixer temperature range", or "pressure outside the pressure range". The operator may add text, images, process data, emoticons, and other information to the operator's response message, and then complete the transmission of the message and the storage of the message. The interaction includes a link to a control action, which may be a preprogrammed action or an operator input action.

[0041] Upon selecting a message from the menu, the operator can "like" or "dislike" the message 260, which will update the "like" or "dislike" count for that message. Updating the "like" or "dislike" count for the message allows the operator to study the frequency of abnormal behavior and estimate which messages are most likely. The operator then sends a response 270 and performs the recommended action. The system checks to see that the process has returned to normal operating conditions 280. A response time is built into the loop to allow the processing unit to return to normal operating conditions. If the process has not yet returned to normal operating conditions, the system returns to the option list 250 and continues to allow the operator to view other relevant options from the menu. Normal operating conditions are those in which the signal returns to the range specified by the recipe. The operator can communicate quickly with the field service personnel to check progress and make suggestions. The checking system continues until the process returns to normal 290. In the present invention, the operating unit includes a sensor and an actuator, wherein information is transmitted from the sensor to the controller, and the controller sends a response to the actuator for the process. The present invention provides for a rapid response when the controller receives a signal indicating that the process is operating outside of the planned range, which is designated as an abnormal condition. As Figure 2, a process 200 is shown. While an operator monitors a process 210, a signal from a sensor on a processing unit is observed. A processor associated with the processing unit includes a memory for storing the signal. The processor also includes a memory for storing a control recipe for operating the processing unit. A control recipe is a program designed to operate the processing unit. The control recipe includes an operating limit for the signal. When the processor detects an abnormal condition 220 or a signal outside the operating limit, the system generates a message 230 indicating that the signal is abnormal or outside the operating limit as specified by the recipe. The generated message can be sent to a monitor of the operating unit. The message can generate a prompt for the operator to respond to the message by entering an operator comment. The message generated by the system includes information about the process, the control recipe, and the type of signal generated by the sensor. The operator then views the comment including possible responses to the message 240, or if there is no relevant comment in the system, the operator can enter a new comment.

[0042] For example, the Experion system (Honeywell International) has a server display screen with a timeline, and it may detect an abnormal condition in a batch from time to time. The system can detect a variety of abnormal conditions. One abnormal condition is a delay, which can be detected by comparing the cycle time of the current stage with the cycle time recorded in the reference batch. In the prior art system, the delay is detected and recorded. Another abnormal condition is out of range. The key performance indicator parameters and master recipes on the unit can be configured by the engineer and monitored at run time. Each key performance indicator has a range, and when the sensor detects that the parameter is out of range, the system will detect an abnormal condition and display an indication on the current timeline. Another abnormal condition will be an alarm, which appears on the display screen. When any of these abnormal conditions are detected, the condition will be displayed in some way, such as a visual notification, and a new context menu will be presented to the operator, which provides an opportunity to enter or select a comment. The operator can then select a comment that presents a suggested action that is considered to be likely to resolve the abnormal condition. Then, after the operator successfully troubleshoots the batch process, the operator can select the comment menu from the available system. The display can then be used to capture batch identification information, locations and / or assets or units involved, and specific parameters for the current batch run. The operator can select one or more problem categories involved in a specific abnormal condition, such as delays, out of range, maintenance issues, equipment issues, etc. The system will then query the event log and run an algorithm to sort the previously entered comments and return a list of previously commented and suggested actions. The top suggested actions are displayed with the ability to expand the list of possible actions in order of relevance, as follows Figure 3 and Figure 4 The operator can then select a comment from the list of historical comments and / or enter his or her own comment into the system via an input device such as a keyboard or a voice message that can be converted to text. After entering a new comment, the system will record the new comment as a comment event. Information contained in this comment event

[0043] The comment can be a preprogrammed response that the operator enters or selects from a menu or allows the system to select a default response. The menu presents a list of options 250 based on the type of processing unit and sensor. The options can be sorted by relevance or historical actions. For example, for a heating mixer, the message can be "mixer heating outside limits", or "temperature outside mixer temperature range", or "pressure outside pressure range". The operator can add text, images, process data, emoticons, and then complete the interaction that may include entering a comment. The interaction includes a link to a control action, which can be a preprogrammed action or an operator input action. The interaction can be completed by inputting from any input device (such as, but not limited to, a computer keyboard, a tablet computer, a smart phone, or an audio input device connected to a computing device).

[0044] When selecting a comment from the menu, the operator can "like" or "dislike" the comment 260, which will update the "like" or "dislike" count of the comment, or rank the comment in relative relevance relative to other comments about the specific abnormal condition. The operator can then perform the suggested action 270 at the operator's discretion. The system checks the output of the sensor to determine whether the process has returned to normal operating conditions 280. If the process has not returned to these normal operating conditions, the operator will continue to view the comments and return to the list of options containing the suggested actions 250, and then continue until the process returns to normal operating conditions 290.

[0045] In one embodiment, the method includes the processing unit communicating with a central data center, and also includes transmitting the generated message to the central data center. The central data center may be a historical database 141 for maintaining a record of abnormal conditions. The central data center or historical database 141 may be located on cloud storage.

[0046] In another embodiment, the processor in the processing unit communicates with the supervisory control center, and also includes transmitting the generated message to the supervisory control center. The supervisory control center can be the plant controller 130, or can be the enterprise controller 138. This enables the event to be transmitted to other plants or other processing units within the plant to allow similar problems to be quickly resolved. The supervisory control center can generate a confirmation message to the local operator of the processing unit. This allows the operator to be aware of additional resources. The supervisory control center can also generate a second message and transmit the second message to the supervisory operator to ensure that the abnormal operating condition is being resolved.

[0047] In another embodiment, the present invention includes a device for recording abnormal behavior in a process and generating a message about the abnormal behavior. The device includes a sensor 122 on a processing unit that generates a signal. The device includes a processor or controller 106, which includes a memory for storing a control recipe, wherein the control recipe is associated with a method for running a product, and wherein the processor includes a memory for storing signals received from the sensor and creating a signal record. The product can be an intermediate product used in a final product. The control recipe includes a processing limit, and a process message is generated when the process exceeds the limit, and wherein the process message includes information about the process, the control recipe, and the type of signal generated by the sensor. The device also includes a device for inputting a response message into the process message. The response message can be an automatic response selected from a potential response menu for returning the processing unit to a normal operating condition. The device also includes a human-machine interface component. The human-machine interface component can be a mobile device, or it can be a computer terminal located at an operator station 116.

[0048] In one embodiment, the apparatus includes a central database or repository, wherein the signal records are transmitted and stored in the central database. The central database may be a database local to the plant, or may be a historical database 141 for recording process information.

[0049] In another embodiment, the device includes a device for inputting photos, commentary text, graphics, and process data. The process data can be collected and plotted at the operator station 132. The operator station 132 may include a scanner and monitor with a keyboard for inputting commentary text, or a microphone with software for converting speech to text.

[0050] In another embodiment, the device includes a search function located in a memory on the processor. The search function can retrieve stored messages from a local data center or historical database 141 for stored messages having the same information about the process, control recipe, and type of signal generated by the sensor. The search function can include operator input to change the parameters of the search of the stored messages.

[0051] In yet another embodiment, the device may also be part of a distributed control system, wherein the distributed control system includes a supervisory control center, or plant controller 130, or enterprise controller 138. The supervisory control center communicates with the operator stations 124 and the processor or unit controllers 122, and with a central data center or historian 141. This provides supervisory control and distribution of messages to similar processing units.

[0052] Discussed below Figure 3 and Figure 4 And the various embodiments used to describe the principles of the present invention in this patent document are only illustrative, and should not be interpreted as limiting the scope of the present invention in any way. It will be understood by those skilled in the art that the principles of the present invention can be implemented in any type of appropriately arranged equipment or system. As mentioned above, many types of industrial processes involve sequential operations such as during product manufacturing or production or in continuous process industries. There are various levels and degrees of automation of batch processing or sequential processing involving various types of human operators. In some cases, the operation sequence is defined outside the process control system and is manually executed, which can be completed according to the recorded instruction list. In other cases, the operation sequence is implemented in the process control system, but it is necessary to interact periodically with the human operator, such as answering questions or confirming that physical actions have been completed by personnel at various stages. In other cases, the operation sequence is fully automated. The human operator may only need to know the sequence to perform various tasks, such as starting the sequence, maintaining situational awareness, or responding to unforeseen or problematic situations.

[0053] With all of these various levels of automation, operators and other personnel involved in the sequence of operations often need to coordinate their daily tasks and supervisory responsibilities with these sequential operations in mind. It can be important when a question needs to be answered, a manual task needs to be performed, a specific piece of equipment needs to be acquired, or a critical processing phase needs to occur. At some point, any operator delay or distraction can result in reduced plant throughput, equipment damage, or lost product. This challenge is compounded as the scope of operator responsibility increases because operators have more sequences running in different pieces of equipment with independent requirements and schedules. As a result, the scope of responsibility that operators can handle without delay and error is limited because the time-based information that operators need is non-existent, fragmented, inaccurate, or expensive for engineers to provide.

[0054] Conventional methods often provide little or no available information about when an operator will need to perform a task or focus on a specific device to support an operational sequence. For example, an operator may only have access to a sequential function chart, which in some cases may be defined according to a standard (such as the ANSI / ISA-88 standard). A sequential function chart is a flowchart that conveys the order of steps in a sequence rather than the timing of those steps. In other cases, an application or a customized display may try to visualize the countdown for the "engineered" timing expectations of a portion of the sequence. However, this requires additional effort to build and maintain, and it does not incorporate real-world changes that occur, such as those that occur due to changed product formulas or seasonal and equipment changes. An operator may load a historical trend of process data values ​​for a specific "golden" batch of product and use the historical trend to estimate the timeline of the current process. However, the selected batch may not be similar to the current sequence, and process trends using multiple batches may display too much data without clearly highlighting the upcoming operations in the current sequence and when they will occur. This visual overload problem is also real (or exacerbated) by simply displaying past and current trend data on top of each other or next to each other. Furthermore, existing visualizations of sequences often only give a fragmented view of what an operator is responsible for, and they typically focus on one sequence or unit of equipment at a time and only indicate when important events are about to occur.

[0055] Currently, any analysis of past anomalies and use of that data to reduce batch cycle time is a manual process that requires additional analytical tools that require manual configuration and increase system cost. The present system will automatically collect relevant data from the operator when a delay or other anomaly occurs, visualize the portion of the batch process and any related equipment with past anomalies, and use that data to predict future problems or provide guidance to the operator to correct the problem without potentially time-consuming manual troubleshooting. It will also provide guidance to the operator to suggest the best path for the batch based on past data.

[0056] The present disclosure describes techniques for predictive time-based control of batch operations or sequential operations. Specifically, the present disclosure relates to a system and method for an operator to quickly identify solutions and take recommended actions in response to abnormal conditions that may occur during batch operations or sequential operations. The ability to prevent potential problems before they cause delays in the batch or use information to quickly troubleshoot and get the batch back on track can reduce the overall batch cycle time. This can increase production and ensure batch quality by eliminating abnormal conditions that may affect quality or cause material loss. Similarly, by providing operators with data on what past operators have learned, the system can automatically provide knowledge transfer between experienced operators and new operators, thereby reducing training time and making shift changes more efficient.

[0057] In the process of the present invention, there is a server, such as the Experion server sold by Honeywell Incorporated. The unit timeline displayed by the server detects an abnormal condition in the batch. The system can detect a variety of abnormal conditions. By comparing whether the cycle time of the current stage is greater than the cycle time recorded in the reference batch, a delay can be detected. The delay has been detected and the delay has been displayed on the unit timeline unit present card. Another abnormal condition is out of range. Key performance indicator parameters on units and recipes can be configured by engineers and monitored at runtime. Each KPI has a range. When the parameter exceeds the range, the system will detect the abnormal condition and display an indication on the unit timeline present card (see Figure 1 : Unit Timeline KPI). The third abnormal condition will be an Alarm, which is displayed on the Unit Timeline. When any of these abnormal conditions are detected, the condition will be visualized on the Unit Timeline and a new context menu will be available for Comment. When the operator successfully troubleshoots the batch and returns the batch to a normal state, the operator can select Comment from the point parameter on the process graphic, the Phase on the Unit Timeline, or the Process Browser. The system will present a display (see Figure 2The system will query the Experion Server Event Log and run an algorithm that will sort the previously entered comments and return a list of previously entered comments and suggested actions, displaying the top suggested actions with the ability to expand and view the full list in order of relevance (see attached flowcharts for "Operator Log Comments," "Suggested Actions Presented When High Level Abnormal Conditions Are Detected," and "Algorithm for Sorting Comments"). The operator can select a comment from the history list and / or can enter their own text into the dialog box by typing or voice input that converts speech to text. The system will record a new event type, the Comment Event, in the existing Experion Server Event Log database. The event will capture the Batch ID, Location or Asset / Unit, Point Parameters, Problem Category, Comment Text, Suggested Action, Operator Username, Date and Time, and Sorting. The operator can "like" or "dislike" the comment and the system will sort it in ascending or descending order. Selecting historical comments for the current comment will sort in ascending order. The algorithm to display the most relevant suggested actions will use a combination of rank, question category, recipe tag name and location to determine overall relevance and will display the top 3 suggested actions to the user with an option to view all.

[0058] Figure 3 A sequence of steps 300 is shown taken from the top, where an abnormal condition occurs in a batch operation 310. Then, within the operating scope of the Experion system (but in principle applicable to other systems), the operator selects a point parameter (such as a unit timeline, process browser or process graphic) from the appropriate screen 320, and then selects the context menu for "Comment". The system presents an operator comment dialog box 330, and the operator then selects the category of the abnormal condition 340 or the problem raised, such as delay, out of range, maintenance requirement or equipment problem. The operator can then enter a comment 350 by voice or text, and can then enter a suggested action 360. The system then records an event 370 in the event log, which may include the batch identification, unit information, point parameters, problem category, comment text and suggested action 380, which is then recorded in the server 390. When no abnormal condition occurs, the display then returns to its normal function 395.

[0059] Figure 4The steps that an operator may take when there is a delay in the batch cycle time compared to a reference batch time taken from top to bottom are shown 400. The operator monitors the batch being processed 410. Then, the system detects an abnormal condition 415. The system presents an indication of the abnormal condition 420 to the operator, who then selects a menu 425 from which comments are displayed. A list of suggested actions and historical comments 430 are shown sorted by relevance. The operator is able to indicate 440 that a comment is "liked" 445 or "disliked" 455. If the comment is "liked" 445, a counter is incremented, while if the comment is "disliked" 455, a counter is decremented. After this point, the system then updates 450 the relative ranking of the comment relative to other comments that have been previously saved. During this process, the operator implements the suggested actions 460 as needed, and in most cases, the batch processing returns to a normal processing 465 condition, and the operator can then return to monitoring the batch processing 470. If the operation has not returned to a normal processing condition, the entire process is repeated 430, wherein the previously highly ranked comments and the implementation of the suggested actions are reviewed.

[0060] Specific implementation plan

[0061] While the following is described in conjunction with specific embodiments, it should be understood that this description is intended to illustrate and not to limit the scope of the foregoing description and the appended claims.

[0062] A first embodiment of the present invention is an apparatus comprising a sensor generating a signal; a processor comprising a memory for storing a control recipe, wherein the control recipe is associated with a method for running a product, and wherein the processor comprises a memory for storing signals received from the sensor, creating a signal record; wherein the control recipe comprises process limits and abnormal conditions, wherein the limits comprise a normal operating range, wherein the abnormal conditions comprise an abnormal operating range outside the normal operating range, and a process message is generated when the sensor detects an abnormal condition, wherein the process message comprises information about the process generated by the sensor, the control recipe, and the signal type; means for an operator to select or enter a comment in response to a response message; and means for maintaining a collection of the comments. An embodiment of the present invention is one, any, or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, wherein the abnormal condition is at least one of a delay, an out-of-range, a maintenance problem, or an equipment problem. An embodiment of the present invention is one, any, or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, wherein the means for maintaining a collection of the comments comprises means for sorting the comments. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, wherein the device for maintaining the collection of comments includes a device for maintaining information related to the abnormal condition and the batch being processed when the abnormal condition occurs. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, wherein the device for sorting the comments communicates with a device that displays a list of the highest recommended actions for resolving the abnormal condition. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, and also includes a human-machine interface component for viewing, entering comments and interacting with comments. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the first embodiment in this paragraph, wherein the human-machine interface component is a mobile device or a computer. One embodiment of the present invention is one, any or all of the embodiments from the previous embodiment in this paragraph to the first embodiment in this paragraph, and also includes integrating the device into a distributed control system, wherein the distributed control system includes a supervisory control center and a central data center, wherein communication is carried out between the processor and the data center, and communication is carried out between the processor and the supervisory control center.

[0063] A second embodiment of the present invention is a method for managing comments in a processing unit, comprising monitoring a plurality of planned operation sequences involving industrial equipment, the planned operation sequences comprising at least one of one or more operation sequences currently being performed using the industrial equipment and one or more operation sequences to be performed using the industrial equipment, wherein the operations are performed according to a recipe containing a key performance indicator; detecting deviations from the key performance indicator, wherein the deviations are determined to be abnormal conditions; identifying comments recorded in the processing unit, wherein the comments are associated with previously identified deviations, and wherein the comments contain a list of recommended actions to be taken to correct the abnormal conditions; determining whether an operator considers any of the list of recommended actions that may correct the abnormal conditions; implementing one or more of the recommended actions; and inputting a ranking of the comments based on the degree of success of the recommended actions in correcting the abnormal conditions. An embodiment of the present invention is one, any one, or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, wherein the abnormal conditions are selected from delays, out-of-range or inadequacies of operations, or requirements for maintenance of equipment. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, and also includes adding additional information to the comment after determining whether the operation sequence has returned to a normal operating condition. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, and also includes adding additional comments after observing an abnormal condition and performing an action to return the operation to a normal operating condition. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, wherein an operator monitors a plurality of planned operation sequences after observing an abnormal operating condition, first selects a point parameter from a process operating system to select a comment context menu, selects a category determined to be the most relevant within the abnormal condition, and then the operator enters a comment about the abnormal condition into an operator comment dialog screen. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, wherein the operator enters a comment including one or more suggested actions to be taken in response to the abnormal condition. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, wherein information related to comments, abnormal conditions and suggested actions are recorded as comment events. One embodiment of the present invention is one, any or all of the previous embodiments in this paragraph to the second embodiment in this paragraph, wherein comments are listed in order based on the ranking of the comments.

[0064] Although there is no further detailed description, it is believed that those skilled in the art can utilize the present invention to the greatest extent by using the foregoing description and can easily determine the essential characteristics of the present invention without departing from the spirit and scope of the present invention to make various changes and modifications of the present invention and adapt it to various usages and conditions. Therefore, the aforementioned preferred specific embodiments should be understood as merely illustrative and not to limit the rest of the present disclosure in any way, and are intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.

[0065] In the foregoing, all temperatures are set forth in degrees Celsius and all parts and percentages are by weight unless otherwise indicated.

Claims

1. A device comprising: The sensor that generates the signal; a processor including a memory for storing a control recipe, wherein the control recipe is associated with running a method for producing a product, and wherein the processor includes a memory for storing a signal received from the sensor, creating a signal record; wherein the control recipe includes process limits and abnormal conditions, the limits include a normal operating range, the abnormal conditions include an abnormal operating range outside the normal operating range, and a process message is generated when the sensor detects the abnormal condition, wherein the process message includes information about the process, the control recipe, and the type of signal generated by the sensor; means for an operator to select or enter a comment in response to the response message; as well as means for maintaining a collection of said comments, wherein said comments contain a list of suggested actions to be taken to correct said abnormal condition; and means for inputting a ranking of the comments based on a degree of success of the suggested actions from a list of suggested actions in correcting the abnormal condition, wherein inputting the ranking of the comments comprises incrementing or decrementing the ranking of the comments based on operator input.

2. The apparatus of claim 1, wherein the abnormal condition is at least one of a delay, an out of range, a maintenance issue, or an equipment issue.

3. The apparatus of claim 1, wherein the means for maintaining the collection of comments comprises means for sorting the comments.

4. The apparatus of claim 1, wherein the means for maintaining the collection of comments includes means for maintaining information related to the abnormal condition and the batch being processed when the abnormal condition occurred.

5. The apparatus of claim 3, wherein the means for ranking the comments is in communication with means for displaying a list of top suggested actions for resolving the abnormal condition.

6. The apparatus according to claim 1 further comprises a human-machine interface component for viewing, inputting and interacting with the comments.

7. The device according to claim 1 also includes integrating the device into a distributed control system, wherein the distributed control system includes a supervisory control center and a central data center, wherein the processor and the data center communicate with each other, and the processor and the supervisory control center communicate with each other.

8. A method for managing comments in a processing unit, comprising: monitoring a plurality of planned operation sequences involving industrial equipment, the planned operation sequences comprising at least one of: one or more operation sequences currently being performed using the industrial equipment and one or more operation sequences to be performed using the industrial equipment, wherein the operations are performed according to a recipe including a key performance indicator; detecting a deviation of the key performance indicator, wherein the deviation is determined to be an abnormal condition; identifying a comment recorded in a processing unit, wherein the comment is associated with a previously identified deviation, and wherein the comment contains a list of suggested actions to be taken to correct the abnormal condition; determining whether an operator considered any item in the list of suggested actions that might correct the abnormal condition; implementing one or more of the suggested actions; and inputting a ranking of the comments based on a degree of success of the suggested action from the list of suggested actions in correcting the abnormal condition, wherein inputting the ranking of the comments includes incrementing or decrementing the ranking of the comments based on operator input.

9. The method of claim 8, further comprising adding additional information to the commentary after determining whether the sequence of operations has returned to normal operating conditions.

10. The method of claim 8, further comprising adding an addition after observing the abnormal condition comment and performing an action to return the operation to a normal operating condition.

Images