243 results about "Process industry" patented technology

A fast computer implemented method generates near-optimal solutions to the multi-objective inventory matching problem by solving for multiple objectives simultaneously and generating multiple non-dominating solutions. The method implements a multi-assignment backjumping algorithm that consists of three steps. The first step is a rappeling step in which a feasible solution is created by applying Iterative Bipartite Matching and maximum flow algorithm. Near-optimal feasible solutions are stored in a non dominated set. The second step is to use a multi-key sort to identify undesirable matches in a given feasible solution. The third step is backlifting the solution by removing undesirable matches from the feasible solution and places those undesirable matches on a no good set of matches. If the feasible solution is non-dominated, a copy is stored in a non-dominated set. The feasible solution is finally provided as input to the repelling step.

A new application of machine vision for process industries is proposed. The invention consists of: (1) estimation of visual quality of products, (2) modeling causal relationship between estimated quality and process variables, and (3) optimization of visual quality using the causal model. This invention can handle the stochastic nature in visual appearance of products that process industries provide, which has been a main obstacle for the success of machine vision in process industries. Also, it opens new tasks in machine vision such as modeling and optimization of visual quality of products.

The invention relates to a process industry system fault analysis device based on complex network theories and a method therefor. The device comprises a system structure information base, a man-machine interaction module, a process data management module, a system network characteristics analysis module and a process fault analysis module. The process fault analysis device and the method provided by the invention can be employed for identifying the key parts of the process system, reducing the process monitoring variables and solving the problem that the selection of monitoring point position depends on people's knowledge or experience; meanwhile, the invention makes the best of real-time data information of the process industry process system, thereby ensuring monitoring over the process fault is more instantaneous and accurate; and the utilization of the system domain knowledge improves the fault recognition and separation capability of the traditional PCA monitoring method.

A composite technology system RETINA that enables intelligent decision synchronization in real time for continuous, discrete and batch process industries is disclosed. RETINA generates and synchronizes the intelligent decisions that affect the performance and profitability of business operations in real time and helps in analysis that are essential for any successful business operations in any manufacturing industries. RETINA combines the real time integration capability; Predictive analytics capability and adaptive real time process modeling capability to generate intelligent risk-reduced business decisions for continuous, discrete and batch manufacturing processes. RETINA unifies the data from disparate sources or in silos, collates, comprehends and analyses the data, and then convert them into actionable information in real time. Correct decisions are generated, streamlined and shared at the appropriate instant of time with right amount of data to the pertinent personnel to eliminate inefficiencies in operations and performance resulting in tangible profitability.

The invention relates to a real time dynamic rescheduling method used for a process industry production scheduling system, aiming at solving the problems of present domestic process industry enterprises that production planning and dispatching have low efficiency, poor accuracy and real-time capability. The real time monitoring method of the invention includes the establishment of a scheduling-optimization math model and the working-out of a dispatching-optimization plan, the completion of the execution of production dispatching instructions and timely tracking calculation; a rolling optimization method includes the arrangement of dispatching time periods, the calculation of the state changes of various production data from present time to scheduling starting time, the generation of the data files of a target model and the establishment of the scheduling-optimization math model. The method of the invention is characterized by real-time, flexibility and promptness, etc. and can realize the integration of the control, the operation, the planning and the management of production-process and enterprise management to realize the balanced and high-effective production of enterprise logistics, production capability and source, thus enhancing the integral production efficiency of enterprises and reducing the cost of production and stock.

The invention discloses a repeated alarm processing method based on data filtering, and belongs to the technical field of alarm management. The method comprises the following steps of: optimally designing variable alarm processing parameters by virtue of variable historical process data, and storing the obtained optimal alarm processing parameters in an alarm parameter database; acquiring real-time process data from a real-time database or a distributed control system (DCS); then obtaining window filtering parameters from the alarm parameter database, and filtering the real-time process data;and finally carrying out repeated alarm judgment on the filtered real-time process data, automatically inhibiting the repeated alarm if the repeated alarm is judged, and otherwise displaying alarm information. The repeated alarm processing method has the beneficial effects that the noise effect in the real-time process data is eliminated, the quantity of occurrence of repeated alarms is reduced and the purpose of alarm management in the process industry is achieved.

The invention discloses an online self-adaptive working condition monitoring and fault diagnosis method for a process industrial course and belongs to the technical field of fault monitoring and diagnosis of complex industrial courses. The method comprises the following steps of firstly, analyzing historical observation data under a normal working condition, introducing an elastic regression network combining Lasso constraints with Ridge constraints to establish an industrial course fault monitoring model on the basis of sparse principal component analysis, and then obtaining a course controllimit to industrial course fault monitoring statistics; during online monitoring of industrial course faults, adopting an order-1 matrix correcting algorithm for resolving a covariance matrix of the online monitoring data, conducting recursion updating on a load matrix of the sparse monitoring model to obtain the course control limit to the course fault monitoring statistics matched with the working condition, and achieving self-adaptive fault detection in the process industry course; finally, according to the detected faults, adopting a contribution plot method for obtaining specific causes of the faults. By means of the method, the faults of the process industry course with complex and changeable working conditions can be self-adaptively monitored for a long time; the method has the advantages of low calculation complexity, high precision, a low report missing rate and the like.

This invention that provides system, method & apparatus for Real Time integration and Analytics (RETINA) to enable proactive decision synchronization in real time in order to minimize the operational risk and maximize the process productivity for process industries such as Oil & Gas Exploration and Fossil fuel power plants is disclosed. RETINA generates and synchronizes the decisions that affect the performance and profitability of business operations in real time and helps in analysis that are essential for any successful business operations. RETINA provides methods and apparatus that combines data from several types of data sources, build models for identifying impending failures, predicting a future state of the process from currently measured process data and provide decision options to business users so that any unwanted opportunity loss such as downtimes or critical equipment failures that are operations risks would be eliminated. RETINA provides methods and apparatus to ensure that correct decisions are taken at the appropriate instant of time with right amount of data to the pertinent personnel to eliminate inefficiencies in operations and performance resulting in tangible profitability.

The invention discloses a saturated self-adjusting controller for a time-varying delay uncertain system. The controller comprises three parts, namely a self-adjusting limiter, a conventional PID controller and an anti-integral saturator, wherein the conventional PID controller generates a control command uc(t) according to the offset of the controlled parameter y(t) and a target value r(t) thereof; the self-adjusting limiter calculates a steady-state gain K of a time-varying delay uncertain object under the corresponding working condition under the driving of a working condition variable s(t), dynamically generates a limiting value according to the K and r(t), timely limits the uc(t) and generates a final control function u(t); and the anti-integral saturator limits the integral function in the PID controller according to the offset of the uc(t) and u(t) in order to solve the possible integral saturation problem. By applying the invention, an engineering technician can conveniently apply effective control to a class of time-varying delay uncertain systems widely present in the process industry on an industrial control system (device) or in the mode of combining a hardware circuit with software programming so as to improve the safety and operating level of the production process.

The invention discloses a method for model mismatching detection and positioning of a multivariate predictive control system in a chemical process. By aiming at the typical hierarchical control system in the traditional process industry, the model mismatching detection and positioning is carried out respectively on a multivariate system and all univariate subsystems in the multivariate system. The method comprises the steps of: acquiring residual errors of the multivariate system in a predicative control layer on the basis of an orthogonal projection method, constructing a monitoring statistic computing engine, and acquiring the residual errors, sensitive to process dynamic characteristic variation only, of the univariate system on the basis of an auxiliary variable identification method.In the invention, closed-loop operation data is adopted directly and additional information of the system is not needed; rapid detection and positioning can be made just by utilizing a small amount of data so that fewer disturbances are made to a working condition; and the mismatching information of process models of all univariate subsystems in the multivariate system can be positioned so as to eliminate the influence of the disturbances. By means of the method disclosed by the invention, the accurate model mismatching information can be obtained rapidly at lower cost, the maintenance cost of the predictive control system can be reduced, the service life of the predicative control system can be prolonged and the gain can be improved.

The invention relates to a sharing platform applied to process control systems in process industry, belonging to the technical field of sharing platforms of process control systems, comprising a process control system, a data exchanging machine, a model server, a report server, a data center server, and a message center server. The invention is characterized in that: the process control system is divided into a plurality of single function modules according to system functions; the data exchanging machine enables the data exchange between the PLC in an external system and the data center server; the model server provides model service to the process control system; the report server provides report service to the process control system; the data center server is the transfer station of data streams, which provides data sharing service to the model server, the report server and the process control system; the message center server is the transfer station for massage flows, which receives the messages of the other modules of the sharing platform and the process control system; all the messages can be seen on the user interface of the process control system. The invention has the advantages that: the development process of process control systems in process industry is simplified, and data service, message service, report service and model service are provided to the process control system.

The invention provides a wireless sensor network system based on dynamic routing, wherein the system is used for the industry. The wireless sensor network system based on dynamic routing comprises a source node cluster, a relay node cluster, a sink node and a control center, and a routing link is composed of a cluster head node of the source node cluster, a cluster head node of the relay node cluster and the sink node. In the idle stage of an industrial network, a test is performed on the link to acquire link quality data, the cluster head nodes are selected according to the link quality data, and a routing link is dynamically selected. According to the wireless sensor network system based on dynamic routing and a dynamic routing selecting method of the system, a clustering structure is provided, a work node is divided into multiple modules, and thus the work node can be suitable for characteristics of the process industry. The periodization characteristic of the process industry is considered, the link test is completed in the idle time slot of the process industry, so that the routing link is dynamically selected, and the reliability of sensor network data transmission is improved. A data retransmission mechanism and an emergency mechanism are introduced, and thus sudden change of environment and other problems can be effectively handled.

The invention discloses a method and a system for tracking the quality of products in a flow industry. Failure events, for example, the index of material components is unqualified, important process parameters are abnormal, important equipment fails to run and production operation does not meet the requirement are automatically triggered, tracked and searched during production of products when the products are finally detected to be unqualified or the products are detected to be unqualified in the middle working section during production of the products through a preset product production process flow, and the failure events are timely showed to a monitor, so that the factor of searching the influence on the quality of the products is increased, and production can be commanded effectively.

The invention discloses a real-time yield prediction method for a hydrocracking device. Field real-time data are processed with a data reconciliation technology, and hydrocracking reaction kinetics parameters are corrected in real time in combination with an improved differential evolution algorithm, so that a mechanism model can accurately describe the actual running condition of the device. On the basis of the corrected model, effects caused by key operation/process conditions such as the raw material density, the sulfur content, the nitrogen content, the reaction temperature, the pressure, the hydrogen-to-oil volume ratio and the like on hydrocracked products are analyzed. Piecewise linearization is performed according to the effect trend, a linear equation is solved, corresponding Delta-Base yield data are acquired, the operation condition is associated with the Delta-Base data with a neutral network modeling technology, a yield surrogate model is established, the yield data calculation speed is increased, real-time prediction of the yield of products of the hydrocracking device is realized, and theoretical support is provided for establishing an accurate plan optimization PIMS (process industry modeling system) model.

The invention discloses a novel method for capturing and separating carbon dioxide, which is applicable to capturing and separating CO2 from tail gas in gas purification, emission reduction of greenhouse gas and process industry and from oil field gas. According to the method, with a high-gravity rotating bed as a rotator and ionic liquid as an absorbent, the absorbent and a mixed gas containing CO2 are in countercurrent or cross-current contact in the high-gravity rotating bed to capture CO2, and the volume-flow ratio of gas to liquid is (50-500):1; the rotating speed of the high-gravity rotating bed is 100-400 rpm; the absorbent is the ionic liquid including amino functional groups or mixture thereof; the pressure in absorption is 0.1-4.0 MPa and the temperature is 15-60 DEG C; and the removal rate of CO2 in raw gas can reach more than 95% (volume). The novel method disclosed by the invention has the advantages of low investment of equipment, small occupied area, low energy consumption, environment friendliness and no corrosion to equipment and the like.

The invention relates to a fluctuation source localization method of multi-loop oscillation of a novel process industry. According to the method, a frequency domain independent component analysis (ICA) is employed to carry out independent component decomposition on industry historical process data; a variable quantity that plays a leading role in fluctuation oscillation and a dominant frequency can be screened; a local directed coherence analysis is carried out on the screened data; and a cause-and-effect relationship graph is used to visually express a cause-and-effect relationship between loop variables, so that a propagation path of a fluctuation interference can be characterized; process priori knowledge is used to simplify the cause-and-effect relationship graph as well as a threshold automatic searching mode is utilized to filter a secondary cause-and-effect relationship branch, so that a main propagation path of fluctuation is obtained and thus a fluctuation source is localized and identified. Compared with the prior art, the technology employed in the invention enables the method to have the following beneficial effects: a signal analysis on a frequency domain is utilized to reveal an essential attribute of oscillation of a multi-loop control system, so that a fluctuation source of the oscillation is determined; and thus, it is beneficial for a factory engineer to carry out follow-up maintenance and repairing work of a fault circuit.

The invention relates to a searching method and system for reasons of a fault event in the process industry. According to the invention, a basic reason resulting in the fault event is automatically searched and sought according to logic and/or time sequence relationship between pre-set fault events and the fault event, and then the basic reason is presented to a monitor to facilitate the monitor to guide the production more effectively.

The embodiment of the invention provides a micro-service architecture of a process industry datamation operation platform. The micro-service architecture comprises a micro-service business architecture and a micro-service technology architecture, wherein the N micro-services are realized by abstracting a whole process industrial model through a high-cohesion low-coupling design mode and DDD domainmodel abstraction, N is greater than 1; the implementation of the high cohesion and low coupling design mode is abstracted through a DDD tactical mode, each domain defines a model, logic and an interface of the domain, relationships among the models are distinguished through UML, and the models with close relationships are placed in the same domain. According to the embodiment of the invention, the problem of MES service rigidity of the traditional process industry is solved, the service expansibility is obtained again, and a comprehensive and reasonable datamation operation platform can be constructed.

The invention discloses a control method of a process industry production system. The control method comprises the following steps: according to the site production situation and the production requirements of the process industry production system, constructing a system model, and drawing a production technological process chart; on the basis of the production technological process chart, determining the production information of the production system, and establishing a target function based on mixed integer linear programming; and taking system production benefit maximization as an optimization object to carry out optimization solution on the target function, and obtaining optimal production information used for controlling the process industry production system. The invention provides a feasible control method of the process industry production system, the control method realizes the combination of the unified modeling and the logistics optimization of the process industry production system, is effective and universal and can provide effective reference information for a production plan of the process industry for controlling.

The invention discloses a data-driven information modeling method for a complex electromechanical system in the process industry. The data-driven information modeling method for the complex electromechanical system in the process industry is employed. The overall modeling process does not need prior knowledge of physical topology. In the modeling process, an information flow relationship is taken as a reference for analyses of coupling relations among different functional components of the system. By taking the anti-noise property and information loss into full consideration, a symbolization process of the system for monitoring time sequences is optimized. By binary coding and decimal decoding of symbolized phase points, the integration between the symbolization process with automated analyses and calculations is achieved. Therefore, the difficulty in building an information model of the complex electromechanical system in the process industry based on monitored data under the noise condition is resolved.