Time series data multi-theme intelligent monitoring method for industrial complex environment

By constructing the preconditions for unit monitoring items and a comprehensive alarm model, the problems of low accuracy and poor adaptability of monitoring and alarm methods in the existing technology are solved, and refined management of equipment operation status and flexibility of alarm system are achieved. Significantly improves the safety and efficiency of power plant operation.

CN118915663AActive Publication Date: 2024-11-08LUCULENT SMART TECHNOLOGIES CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202410973710.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-08
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

The existing monitoring and alarm methods have low accuracy and are prone to false alarms and omissions in complex and changing equipment operation environments. It is difficult to manage the operating status of the equipment in a refined manner, and it is impossible to effectively handle multi-theme monitoring items and comprehensive Alarm model.

Method used

By constructing the preconditions for unit monitoring items, defining the alarm status details, using Boolean logic and multi-dimensional tensor operations and other methods to perform nonlinear transformation and rule application of data sources, combining convolution and Laplace transformation, a comprehensive alarm model is generated Determine the alarm status of the data source and realize refined management of the operating status of the equipment.

Benefits of technology

It significantly reduces the false alarm rate and workload of the monitoring system, improves the stability and reliability of the system, realizes refined management of the operating status of the equipment, improves the flexibility and adaptability of the alarm system, and can reflect more timely. The equipment operation status optimizes the overall performance of the monitoring system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915663A_ABST
    Figure CN118915663A_ABST
Patent Text Reader

Abstract

The invention discloses a time series data multi-theme intelligent monitoring method for an industrial complex environment, and relates to the technical field of power plant monitoring and alarming, and the method comprises the steps: constructing a unit monitoring item precondition; defining alarm state details through the themes of the unit monitoring items; and the data source is recalculated through judgment of the comprehensive alarm model. According to the time sequence data multi-theme intelligent monitoring method oriented to the industrial complex environment, the false alarm rate and the workload of a monitoring system are reduced by constructing the set monitoring item preconditions, the stability and the reliability of the system are improved, the delicacy management of the equipment operation state is realized by constructing the set monitoring item themes, and the time sequence data multi-theme intelligent monitoring method oriented to the industrial complex environment is suitable for the industrial complex environment. According to the method, the operation state of equipment is accurately monitored, potential problems are found in real time, the operation safety and efficiency of a power plant are improved, a data source is recalculated through judgment of a comprehensive alarm model, the flexibility and adaptability of an alarm system are improved, and better effects are achieved in the aspects of alarm accuracy, adaptability and efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power plant monitoring and alarm technology, and in particular to a multi-topic intelligent monitoring method of time series data for complex industrial environments. Background Art

[0002] In recent years, with the continuous improvement of industrial automation and intelligence, the role of power plant monitoring systems in power production and management has become increasingly prominent. Traditional power plant monitoring systems mostly adopt a design based on relational databases, which collect and store a large amount of sensor data to monitor the operating status of equipment in real time. However, with the explosive growth of data volume and the diversification of monitoring needs, the shortcomings of traditional relational databases in processing high-frequency data, real-time and scalability have gradually been exposed. In order to solve these problems, time series databases came into being. Time series databases are specially optimized for time series data, can efficiently process and store large-scale time series data, provide fast read and write performance and efficient query capabilities, and have become an important technical foundation for modern power plant monitoring systems.

[0003] At present, the application of time series database in power plant monitoring is mainly concentrated in real-time data collection, storage and query. Using time series database, power plants can realize real-time monitoring of equipment operation status and efficient query of historical data, thereby improving the safety and stability of power plant operation. However, with the continuous improvement of power plant monitoring needs, relying solely on real-time data collection and storage can no longer meet the complex and changing monitoring needs. How to build a more intelligent and comprehensive monitoring and alarm system based on time series database has become one of the current research hotspots.

[0004] Although the application of time series databases in power plant monitoring systems has made significant progress, the existing monitoring and alarm methods still have many shortcomings. First, traditional monitoring and alarm methods usually use simple threshold settings and logical judgments, which are difficult to adapt to the complex and changeable equipment operating environment. This method is not only prone to false alarms and missed alarms, but also difficult to finely manage the equipment operating status. Secondly, the existing monitoring and alarm system lacks effective methods for handling multi-topic monitoring items and comprehensive alarm models, and cannot achieve comprehensive analysis and processing of multi-dimensional data. Especially when faced with data source recalculation and complex alarm conditions, the existing system often seems powerless and difficult to provide accurate and reliable alarm information. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the existing monitoring and alarm methods have low accuracy, are prone to false alarms and missed alarms, are difficult to adapt to the complex and changeable equipment operating environment, and are difficult to finely manage the equipment operating status.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a multi-topic intelligent monitoring method for time series data in complex industrial environments, including constructing preconditions for unit monitoring items; defining alarm status details through unit monitoring item topics; and recalculating data sources through comprehensive alarm model judgment.

[0008] As a preferred solution of the multi-topic intelligent monitoring method of time series data for complex industrial environments described in the present invention, wherein: the construction of the preconditions for unit monitoring items includes collecting precondition data for unit monitoring items, including equipment status class, environmental parameter class, maintenance status class, historical alarm status class and equipment start-stop status class;

[0009] For equipment status preconditions, if the boiler temperature is not between 150°C and 250°C, the alarm monitoring will not be activated; if the generator speed is less than 1800 rpm, the alarm monitoring will not be activated;

[0010] For environmental parameter preconditions, if the ambient temperature is not between -10℃ and 40℃, the alarm monitoring will not be activated; if the ambient humidity is not between 20% and 80%, the alarm monitoring will not be activated;

[0011] For maintenance status preconditions, if the device is in maintenance status, alarm monitoring will not be started;

[0012] For historical alarm status preconditions, if there are unprocessed historical alarms, new alarm monitoring will not be started;

[0013] For equipment start / stop status preconditions, if the equipment is not started or the running time is less than 30 minutes, the alarm monitoring will not be started.

[0014] As a preferred solution of the multi-topic intelligent monitoring method of time series data for complex industrial environments described in the present invention, wherein: the construction of the unit monitoring item precondition includes defining the precondition using Boolean logic, and each precondition is defined by a Boolean matrix P i Indicates that P i Indicates the alarm status of the i-th device, 1 indicates alarm, 0 indicates normal, and the overall precondition is expressed as:

[0015]

[0016] Among them, ⊙ represents the bit-by-bit multiplication of elements, and n represents the number of preconditions;

[0017] If P total If all elements in are 1, the precondition is met and the monitoring and alarm work continues, otherwise it does not.

[0018] As a preferred solution of the multi-topic intelligent monitoring method for time series data in a complex industrial environment described in the present invention, wherein: the definition of the alarm status details through the unit monitoring item theme includes constructing a unit monitoring item theme, and the monitoring item theme provides monitoring alarm rule details for defining the alarm status details, including equipment over-limit theme, assessment condition theme, input and exit status, equipment start and stop theme, interface monitoring theme, characteristic value theme, packaging point theme, and wall temperature monitoring theme, binding the data source with the monitoring item theme rule to generate alarm information;

[0019] Perform nonlinear transformation on the data source vector D, where the data source vector is D = [D1, D2, ..., D m ], nonlinear transformation can be performed, expressed as

[0020] σ(D)=[σ(D1),σ(D2),…,σ(D m )]

[0021]

[0022] Where D represents the data source vector, which is the data from various sensors or monitoring devices, and the vector dimension is m. σ(D) represents the nonlinear transformation of the data source vector. i ) represents the transformation result of the i-th data source value;

[0023] Working with multidimensional tensors and regular tensors Apply rules and tensor product operations to the data source, expressed as:

[0024]

[0025] in, Represents a multidimensional tensor, which is the regular matrix of the i-th monitoring item topic, with dimensions (p×q×r), M i,juv represents the element of the i-th tensor at position (j,u,v), Represents the rule tensor, which is the matrix of the i-th rule, R i,uvk represents the element of the ith rule tensor at position (u, v, k), A1 represents the intermediate alarm state vector obtained by tensor product operation and rule application, and A 1,jk represents the element at position (j, k) after the tensor product operation and the application of the rule;

[0026] Perform pooling operation on the data source, expressed as:

[0027]

[0028] Among them, pool(D) ijRepresents the maximum pooling result at position (i,j), (u,v)∈N(i,j)'

[0029] Combining convolution tensors and weight coefficient α j Perform convolution operation, expressed as:

[0030]

[0031] Among them, A2 represents the intermediate alarm state vector obtained by pooling operation and convolution operation.

[0032] As a preferred solution of the multi-topic intelligent monitoring method of time series data for complex industrial environments described in the present invention, the alarm status details defined by the unit monitoring item theme include Fourier transforming the data source and outputting frequency domain information, which is expressed as:

[0033]

[0034] in, Represents the Fourier transform of the data source vector, outputs frequency domain information, D(t) represents the value of the data source signal at time t, and f represents the specific frequency component in the Fourier transform result

[0035] Combined weight coefficient β k The output is expressed as:

[0036]

[0037] Among them, A3 represents the weight coefficient, which represents the weight of the k-th Fourier transform;

[0038] Perform Laplace transform on the data source, and the transform from the output time domain to the complex frequency domain is expressed as:

[0039]

[0040] in, represents the Laplace transform of the data source vector, which is the transformation from the time domain to the complex frequency domain, and s represents a complex variable;

[0041] Combined weight coefficient γ l , expressed as:

[0042]

[0043] Among them, γ l represents the weight coefficient, represents the weight of the lth Laplace transform, and A4 represents the intermediate alarm state vector obtained by Laplace transform and the weight coefficient;

[0044] The results of all parts are superimposed, and the final alarm state vector A is output through a nonlinear activation function. The comprehensive alarm model is expressed as:

[0045] A=f(A1+A2+A3+A4)

[0046]

[0047] Among them, f(z) j represents the final nonlinear activation function, z represents the combination result of the intermediate alarm state vector, and z j Represents the jth element in vector z.

[0048] As a preferred solution of the multi-topic intelligent monitoring method of time series data for complex industrial environments described in the present invention, wherein: the alarm status details defined through the unit monitoring item topic include monitoring items and associated unit monitoring item topics. If the alarm conditions in the monitoring item topic details are met, the unit real-time alarm status and the unit historical alarm status will be generated. The alarm status will include event start time, data source value, alarm duration, maximum value within the duration, and minimum value information;

[0049] When the alarm status changes, the previous alarm will be canceled, a new alarm will be generated, and the real-time alarm status and historical alarm status of the unit will be recorded.

[0050] As a preferred solution of the multi-topic intelligent monitoring method of time series data for complex industrial environments described in the present invention, the recalculation of the data source through the comprehensive alarm model judgment includes, for the units that need to adjust the historical alarm subject rules, re-executing the comprehensive alarm model judgment through the monitoring alarm recalculation function, recalculating the bound data source according to the new subject rules, and then specifying the recalculation time period to automatically generate the latest real-time monitoring item alarm status and the unit historical alarm status.

[0051] Another object of the present invention is to provide a multi-topic intelligent monitoring system for time series data in complex industrial environments, which can define alarm status details through unit monitoring item themes, solving the problem that current monitoring and alarm methods have difficulty in fine-grained management of equipment operating status.

[0052] As a preferred solution of the multi-topic intelligent monitoring system of time series data for complex industrial environments described in the present invention, it includes: a unit monitoring item precondition construction module, a comprehensive alarm model construction module, and a data source recalculation module; the unit monitoring item precondition construction module is used to construct the unit monitoring item precondition; the comprehensive alarm model construction module is used to construct a comprehensive alarm model through the unit monitoring item theme definition alarm status details; the data source recalculation module is used to re-execute the comprehensive alarm model judgment through the monitoring alarm recalculation function.

[0053] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for multi-topic intelligent monitoring of time series data in a complex industrial environment.

[0054] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a multi-topic intelligent monitoring method for time series data in a complex industrial environment.

[0055] Beneficial effects of the present invention: The present invention provides a multi-topic intelligent monitoring method for time series data in complex industrial environments, which realizes effective filtering and control of monitoring and alarm work by constructing pre-conditions for unit monitoring items, significantly reduces the false alarm rate and workload of the monitoring system, and improves the stability and reliability of the system. By constructing unit monitoring item themes and defining alarm status details in detail, the method realizes refined management of equipment operating status, accurately monitors equipment operating status, discovers potential problems in real time, and improves the safety and efficiency of power plant operation. The method recalculates the data source through comprehensive alarm model judgment, improves the flexibility and adaptability of the alarm system, can reflect the equipment operating status more promptly, and optimizes the overall performance of the monitoring system. The present invention achieves better results in terms of alarm accuracy, adaptability and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0057] Figure 1 An overall flow chart of a multi-topic intelligent monitoring method for time series data in a complex industrial environment provided for the first embodiment of the present invention.

[0058] Figure 2 An architectural diagram of a multi-topic intelligent monitoring method for time series data in a complex industrial environment provided for the first embodiment of the present invention.

[0059] Figure 3 A business architecture diagram of a multi-topic intelligent monitoring method for time series data in complex industrial environments provided for the first embodiment of the present invention.

[0060] Figure 4 An overall flow chart of a multi-topic intelligent monitoring system for time series data in complex industrial environments provided for the third embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] Example 1

[0063] Reference Figure 1-Figure 3 , which is an embodiment of the present invention, provides a multi-topic intelligent monitoring method for time series data in a complex industrial environment, including:

[0064] S1: Construct the preconditions for unit monitoring items.

[0065] Furthermore, Figure 2 1 is a system architecture diagram of an embodiment of the present invention, which shows the relationship between the DCS data source, the time series database, the monitoring subject and the power plant monitoring alarm system.

[0066] It should be noted that the DCS data source is forwarded to the time series database through the gateway for storage. The time series database stores the analog quantities, switch quantities, characteristic values, and packaging points in the DCS according to the time series. According to the data source type, compression modes such as dynamic threshold, jump storage, timing storage, lossy storage, and lossless storage are realized.

[0067] The time series database pushes high-concurrency, fast-changing data to the power plant monitoring and alarm system through MQTT data subscription, and provides an Rpc batch query interface to collect statistical information such as time, day, month, and year of the statistical data source.

[0068] It should be noted that the power plant monitoring and alarm system provides equipment over-limit topics, assessment condition topics, input and output status, equipment start and stop topics, interface monitoring topics, characteristic value topics, packaging point topics, and wall temperature monitoring topics, and each topic is configured with a corresponding data source list to monitor the operating alarm status of each unit. Figure 3This is a business architecture diagram of a multi-topic alarm system. The diagram shows the relationship between unit monitoring items, unit monitoring item preconditions, unit monitoring item topics, unit alarm status, unit monitoring item recalculation, and the power plant monitoring alarm system.

[0069] Furthermore, the preconditions for the monitoring items of the new units are that there are many operating components in the power plant units, many of which are relatively problematic and there are correlations between the components. Therefore, providing a unit alarm monitoring method with configurable preconditions will solve such problems well. When the preconditions are not met, the monitoring and alarm work will not be carried out. When the preconditions are met, the monitoring and alarm work will continue.

[0070] It should be noted that the collection of pre-condition data for unit monitoring items includes equipment status, environmental parameters, maintenance status, historical alarm status, and equipment start and stop status;

[0071] For equipment status preconditions, if the boiler temperature is not between 150°C and 250°C, the alarm monitoring will not be activated; if the generator speed is less than 1800 rpm, the alarm monitoring will not be activated;

[0072] For environmental parameter preconditions, if the ambient temperature is not between -10℃ and 40℃, the alarm monitoring will not be activated; if the ambient humidity is not between 20% and 80%, the alarm monitoring will not be activated;

[0073] For maintenance status preconditions, if the device is in maintenance status, alarm monitoring will not be started;

[0074] For historical alarm status preconditions, if there are unprocessed historical alarms, new alarm monitoring will not be started;

[0075] For equipment start / stop status preconditions, if the equipment is not started or the running time is less than 30 minutes, the alarm monitoring will not be started.

[0076] It should also be noted that the preconditions are defined using Boolean logic, and each precondition is represented by a Boolean matrix P i Indicates that P i Indicates the alarm status of the i-th device, 1 indicates alarm, 0 indicates normal, and the overall precondition is expressed as:

[0077]

[0078] Among them, ⊙ represents the bit-by-bit multiplication of elements, and n represents the number of preconditions;

[0079] If P total If all elements in are 1, the precondition is met and the monitoring and alarm work continues, otherwise it does not.

[0080] S2: Define the alarm status details through the unit monitoring item topic.

[0081] Furthermore, a new unit monitoring item topic is created. The monitoring item topic mainly provides monitoring alarm rule details, which are used to define alarm status details, including equipment over-limit topic, assessment condition topic, input and output status, equipment start and stop topic, interface monitoring topic, characteristic value topic, packaging point topic, and wall temperature monitoring topic. The data source is bound to the monitoring item topic rules to facilitate assigning specific meaning to each time block of the data source, thereby generating alarm information.

[0082] It should be noted that the unit monitoring item theme is constructed, and the monitoring item theme provides monitoring alarm rule details, which are used to define the alarm status details, including equipment over-limit theme, assessment condition theme, input and exit status, equipment start and stop theme, interface monitoring theme, characteristic value theme, packaging point theme, and wall temperature monitoring theme. The data source is bound to the monitoring item theme rules to generate alarm information;

[0083] Perform nonlinear transformation on the data source vector D, where the data source vector is D = [D1, D2, ..., D m ], nonlinear transformation can be performed, expressed as

[0084] σ(D)=[σ(D1),σ(D2),…,σ(D m )]

[0085]

[0086] Where D represents the data source vector, which is the data from various sensors or monitoring devices, and the vector dimension is m. σ(D) represents the nonlinear transformation of the data source vector. i ) represents the transformation result of the i-th data source value;

[0087] Working with multidimensional tensors and regular tensors Apply rules and tensor product operations to the data source, expressed as:

[0088]

[0089] in, Represents a multidimensional tensor, which is the regular matrix of the i-th monitoring item topic, with dimensions (p×q×r), M i,juv represents the element of the i-th tensor at position (j,u,v), Represents the rule tensor, which is the matrix of the i-th rule, R i,uvk represents the element of the ith rule tensor at position (u, v, k), A1 represents the intermediate alarm state vector obtained by tensor product operation and rule application, and A 1,jkrepresents the element at position (j, k) after the tensor product operation and the application of the rule;

[0090] Perform pooling operation on the data source, expressed as:

[0091]

[0092] Among them, pool(D) ij Represents the maximum pooling result at position (i,j), (u,v)∈N(i,j)'

[0093] Combining convolution tensors and weight coefficient α j Perform convolution operation, expressed as:

[0094]

[0095] Among them, A2 represents the intermediate alarm state vector obtained by pooling operation and convolution operation.

[0096] It should also be noted that the data source is Fourier transformed to output frequency domain information, which is expressed as:

[0097]

[0098] in, Represents the Fourier transform of the data source vector, outputs frequency domain information, D(t) represents the value of the data source signal at time t, and f represents the specific frequency component in the Fourier transform result

[0099] Combined weight coefficient β k The output is expressed as:

[0100]

[0101] Among them, A3 represents the weight coefficient, which represents the weight of the k-th Fourier transform;

[0102] Perform Laplace transform on the data source, and the transform from the output time domain to the complex frequency domain is expressed as:

[0103]

[0104] in, represents the Laplace transform of the data source vector, which is the transformation from the time domain to the complex frequency domain, and s represents a complex variable;

[0105] Combined weight coefficient γ l , expressed as:

[0106]

[0107] Among them, γ lrepresents the weight coefficient, represents the weight of the lth Laplace transform, and A4 represents the intermediate alarm state vector obtained by Laplace transform and the weight coefficient;

[0108] The results of all parts are superimposed, and the final alarm state vector A is output through a nonlinear activation function. The comprehensive alarm model is expressed as:

[0109] A=f(A1+A2+A3+A4)

[0110]

[0111] Among them, f(z) j represents the final nonlinear activation function, z represents the combination result of the intermediate alarm state vector, and z j Represents the jth element in vector z.

[0112] S3: Recalculate the data source through comprehensive alarm model judgment.

[0113] Furthermore, a new unit monitoring item is created and associated with the unit monitoring item topic in S2. When the alarm condition in the monitoring item topic details is met, the unit real-time alarm status and unit historical alarm status will be generated. The alarm status will include information such as event start time, data source value, alarm duration, maximum value within the duration, minimum value, etc. When the alarm status changes, the previous alarm will be canceled, a new alarm will be generated, and the unit real-time alarm status and unit historical alarm status will be recorded.

[0114] It should be noted that in addition to establishing a unit monitoring item recalculation task, the present invention also provides a unit monitoring alarm recalculation function. For units that need to adjust historical alarm subject rules, the monitoring alarm recalculation function can be used to recalculate the bound data source according to new subject rules. It can support recalculation of specified time periods and quickly generate the latest real-time monitoring item alarm status and unit historical alarm status.

[0115] It should also be noted that the real-time alarm status will be pushed in real time through EventHubs and WebSocket, and the start time, end time of the alarm end and the generation of new alarms, and the maximum and minimum values ​​of the data source during the alarm period are stored in PostgreSQL.

[0116] Example 2

[0117] An embodiment of the present invention provides a multi-topic intelligent monitoring method for time series data in a complex industrial environment. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0118] First, the test objects are five units of a power plant, which are numbered as unit A, unit B, unit C, unit D and unit E. The five units are subjected to comparative experiments by applying the monitoring and alarm method of the present invention and the monitoring and alarm method of the prior art.

[0119] Each unit is equipped with necessary sensors, including temperature sensors, speed sensors, ambient temperature sensors, ambient humidity sensors, etc. Ensure that the sensors are connected to the time series database and can collect and store data in real time.

[0120] Equipment status prerequisites: boiler temperature is between 150℃ and 250℃, and generator speed is not less than 1800 rpm.

[0121] Environmental parameter prerequisites: ambient temperature between -10℃ and 40℃, ambient humidity between 20% and 80%.

[0122] Maintenance status prerequisite: The device is not in maintenance status.

[0123] Historical alarm status category prerequisite: There are no unprocessed historical alarms.

[0124] Equipment start / stop status prerequisite: The equipment has been running for more than 30 minutes.

[0125] Each unit collects data such as temperature, speed, ambient temperature, and ambient humidity in real time to ensure the accuracy and timeliness of the data. The collected data is compared with the set preconditions. If the conditions are met, the next stage is entered, otherwise the alarm monitoring is stopped. According to the subject rules of the monitoring items, nonlinear transformation and multidimensional tensor operations are performed on the data source to generate a preliminary alarm state. Pooling operations, Fourier transforms, and Laplace transforms are performed on the preliminary alarm state, and the weight coefficients are combined for calculation to finally generate an alarm state vector.

[0126] For situations where historical alarm rules need to be adjusted, the comprehensive alarm model judgment is re-executed to generate the latest alarm status. The alarm status and related parameters of each unit are recorded and compared with the alarm system of the existing technology.

[0127] Table 1 Experimental data table

[0128]

[0129] In terms of the number of alarms and false alarms, it can be seen from the table that the number of alarms of the units (unit A, unit B and unit E) using the present invention is controlled within a reasonable range, and the number of false alarms is significantly lower than that of the units in the prior art (unit C and unit D). The number of alarms of unit A is 15 times, the number of false alarms is only 1, and the alarm accuracy rate is as high as 93.33%; in contrast, the number of alarms of unit C is 20 times, the number of false alarms is as high as 5 times, and the alarm accuracy rate is only 75.00%.

[0130] In terms of alarm response time, the table data shows that the unit using the present invention performs well in terms of alarm response time. The alarm response time of unit B is 4 seconds, which is much lower than 8 seconds of unit C and 9 seconds of unit D.

[0131] In terms of data recalculation time, the data recalculation time of unit A is 10 seconds, and that of unit B is 12 seconds, while units C and D of the prior art require 20 seconds and 25 seconds respectively.

[0132] In terms of alarm accuracy, it can be seen from the table that the alarm accuracy of the unit using the present invention is significantly higher than that of the prior art unit. The alarm accuracy of unit E is as high as 93.75%, while the alarm accuracy of unit D is only 72.73%.

[0133] In summary, the present invention achieves better results in terms of alarm accuracy, adaptability and efficiency.

[0134] Example 3

[0135] Reference Figure 4 , which is an embodiment of the present invention, provides a multi-topic intelligent monitoring system for time series data in complex industrial environments, including a unit monitoring item precondition building module, a comprehensive alarm model building module, and a data source recalculation module.

[0136] The unit monitoring item precondition construction module is used to construct the unit monitoring item precondition, and the comprehensive alarm model construction module is used to construct the comprehensive alarm model through the unit monitoring item subject definition alarm status details. The data source recalculation module is used to re-execute the comprehensive alarm model judgment through the monitoring alarm recalculation function.

[0137] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0138] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0139] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0140] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-topic intelligent monitoring method for time series data in complex industrial environments, characterized in that: include: Construct preconditions for unit monitoring items; Define the alarm status details through the unit monitoring item theme; The data source is recalculated through comprehensive alarm model judgment.

2. The multi-topic intelligent monitoring method for time series data in a complex industrial environment according to claim 1, characterized in that: The constructing of the unit monitoring item preconditions includes collecting the unit monitoring item precondition data, including equipment status class, environmental parameter class, maintenance status class, historical alarm status class and equipment start and stop status class; For equipment status preconditions, if the boiler temperature is not between 150°C and 250°C, the alarm monitoring will not be activated; if the generator speed is less than 1800 rpm, the alarm monitoring will not be activated; For environmental parameter preconditions, if the ambient temperature is not between -10℃ and 40℃, the alarm monitoring will not be activated; if the ambient humidity is not between 20% and 80%, the alarm monitoring will not be activated; For maintenance status preconditions, if the device is in maintenance status, alarm monitoring will not be started; For historical alarm status preconditions, if there are unprocessed historical alarms, new alarm monitoring will not be started; For equipment start / stop status preconditions, if the equipment is not started or the running time is less than 30 minutes, the alarm monitoring will not be started.

3. The multi-topic intelligent monitoring method for time series data in a complex industrial environment as claimed in claim 2, characterized in that: The construction of the unit monitoring item preconditions includes defining the preconditions using Boolean logic, each precondition is represented by a Boolean matrix P i Indicates that P i Indicates the alarm status of the i-th device, 1 indicates alarm, 0 indicates normal, and the overall precondition is expressed as: Among them, ⊙ represents the bit-by-bit multiplication of elements, and n represents the number of preconditions; If P total If all elements in are 1, the precondition is met and the monitoring and alarm work continues, otherwise it does not.

4. The multi-topic intelligent monitoring method for time series data in a complex industrial environment as claimed in claim 3, characterized in that: Defining the alarm status details through the unit monitoring item theme includes constructing the unit monitoring item theme, the monitoring item theme provides monitoring alarm rule details, which are used to define the alarm status details, including the equipment over-limit theme, the assessment condition theme, the input and output status, the equipment start and stop theme, the interface monitoring theme, the characteristic value theme, the packaging point theme, and the wall temperature monitoring theme, binding the data source with the monitoring item theme rules, and generating alarm information; Perform nonlinear transformation on the data source vector D, where the data source vector is D = [D1, D2, ..., D m ], nonlinear transformation can be performed, expressed as σ(D)=[σ(D1),σ(D2),...,σ(D m )] Where D represents the data source vector, which is the data from various sensors or monitoring devices, and the vector dimension is m. σ(D) represents the nonlinear transformation of the data source vector. i ) represents the transformation result of the i-th data source value; Working with multidimensional tensors and regular tensors Apply rules and tensor product operations to the data source, expressed as: in, Represents a multidimensional tensor, which is the regular matrix of the i-th monitoring item topic, with dimensions (p×q×r), M i,juv represents the element of the i-th tensor at position (j,u,v), Represents the rule tensor, which is the matrix of the i-th rule, R i,uvk represents the element of the ith rule tensor at position (u, v, k), A1 represents the intermediate alarm state vector obtained by tensor product operation and rule application, A1, j k represents the element at position (j, k) after the tensor product operation and the application of the rule; Perform pooling operation on the data source, expressed as: Among them, pool(D) ij Represents the maximum pooling result at position (i,j), (u,v)∈N(i,j)' Combining Convolution Tensors and weight coefficient α j Perform convolution operation, expressed as: Among them, A2 represents the intermediate alarm state vector obtained by pooling operation and convolution operation.

5. The multi-topic intelligent monitoring method for time series data in a complex industrial environment as claimed in claim 4, characterized in that: Defining the alarm status details through the unit monitoring item theme includes performing Fourier transform on the data source and outputting frequency domain information, which is expressed as: in, Represents the Fourier transform of the data source vector, outputs frequency domain information, D(t) represents the value of the data source signal at time t, and f represents the specific frequency component in the Fourier transform result Combined with the weight coefficient βk output, it is expressed as: Among them, A3 represents the weight coefficient, which represents the weight of the k-th Fourier transform; Perform Laplace transform on the data source, and the transform from the output time domain to the complex frequency domain is expressed as: in, represents the Laplace transform of the data source vector, which is the transformation from the time domain to the complex frequency domain, and s represents a complex variable; Combined with the weight coefficient γl, it is expressed as: Among them, γl represents the weight coefficient, which represents the weight of the lth Laplace transform, and A4 represents the intermediate alarm state vector obtained by Laplace transform and weight coefficient; The results of all parts are superimposed, and the final alarm state vector A is output through a nonlinear activation function. The comprehensive alarm model is expressed as: A=f(A1+A2+A3+A4) Among them, f(z) j represents the final nonlinear activation function, z represents the combination result of the intermediate alarm state vector, and z j Represents the jth element in vector z.

6. The multi-topic intelligent monitoring method for time series data in a complex industrial environment as claimed in claim 5, characterized in that: The alarm status details defined through the unit monitoring item theme include monitoring items and associated unit monitoring item themes. If the alarm conditions in the monitoring item theme details are met, the unit real-time alarm status and unit historical alarm status will be generated. The alarm status will include event start time, data source value, alarm duration, maximum value within the duration, and minimum value information; When the alarm status changes, the previous alarm will be canceled, a new alarm will be generated, and the real-time alarm status and historical alarm status of the unit will be recorded.

7. The multi-topic intelligent monitoring method for time series data in a complex industrial environment according to claim 6, characterized in that: The recalculation of the data source through the comprehensive alarm model judgment includes, for the units that need to adjust the historical alarm subject rules, re-executing the comprehensive alarm model judgment through the monitoring alarm recalculation function, recalculating the bound data source according to the new subject rules, and then specifying the recalculation time period, automatically generating the latest real-time monitoring item alarm status and unit historical alarm status.

8. A system using a multi-topic intelligent monitoring method for time series data in a complex industrial environment as claimed in any one of claims 1 to 7, characterized in that: It includes the unit monitoring item precondition construction module, the comprehensive alarm model construction module, and the data source recalculation module; The unit monitoring item precondition construction module is used to construct the unit monitoring item precondition; The comprehensive alarm model construction module is used to construct a comprehensive alarm model by defining the alarm status details through the unit monitoring item theme; The data source recalculation module is used to re-execute the comprehensive alarm model judgment through the monitoring alarm recalculation function.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a multi-topic intelligent monitoring method for time series data in a complex industrial environment as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a multi-topic intelligent monitoring method for time series data in a complex industrial environment as described in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Fault early warning system and determine method for wind turbine generator system

    CN107038453A

  • Early warning mattress based on signal induction

    CN112932171A

  • Environment monitoring method, system and platform and storage medium

    CN113138865A

  • Distributed photovoltaic power generation real-time monitoring method and system

    CN115173550A

  • Energy storage EMS intelligent monitoring system

    CN116846077A