CN113239187B - Monitoring method based on multi-level industrial structure knowledge block division - Google Patents
Monitoring method based on multi-level industrial structure knowledge block division Download PDFInfo
- Publication number
- CN113239187B CN113239187B CN202110393994.8A CN202110393994A CN113239187B CN 113239187 B CN113239187 B CN 113239187B CN 202110393994 A CN202110393994 A CN 202110393994A CN 113239187 B CN113239187 B CN 113239187B
- Authority
- CN
- China
- Prior art keywords
- level
- statistics
- sub
- block
- residual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 164
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000004519 manufacturing process Methods 0.000 claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims description 94
- 230000008569 process Effects 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000000638 solvent extraction Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 8
- 238000012806 monitoring device Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000009826 distribution Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000009776 industrial production Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000013067 intermediate product Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a monitoring method based on multi-level industrial structure knowledge block division, which comprises the following steps: constructing a multi-level knowledge graph of the industrial process; performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold; and obtaining global monitoring results and local monitoring results of the multi-level sub-blocks according to the multi-level sub-block statistical data. According to the embodiment of the invention, through the method, a multi-level knowledge graph of an industrial process is constructed by using a small amount of simple expert domain knowledge, sub-block division is carried out by taking the nodes of the multi-level knowledge graph as the basis, and finally, principal component statistics and residual statistics are counted according to the multi-level sub-blocks, so that the accurate positioning of abnormal nodes is realized through a contribution graph backtracking strategy.
Description
Technical Field
The invention relates to the technical field of industrial knowledge automation, in particular to a monitoring method based on multi-level industrial structure knowledge block division.
Background
With the tremendous advances in modern communication, computer, and sensor technologies, most modern large-scale process production processes have characteristics that are not available in traditional processes. For example, numerous operating units, numerous monitoring variables, and strongly coupled variable dependencies. These special characteristics make it increasingly difficult to guarantee the safety of large-scale process industrial production in the prior art.
Related studies have shown that a distributed monitoring system established using a block or scatter monitoring mode can address the safety of such large-scale process industrial production, and the strategy generally achieves better monitoring performance than the traditional single monitoring method, such as improving the abnormal state detection rate, reducing the complexity of the monitoring system, and the like. The key points for guaranteeing the performance of the decentralized monitoring strategy are as follows: the production process block division should have the ability to accurately describe the abnormal conditions; the running state of each partition block should be reflected in the statistical index of the global abnormal state rapidly and sensitively; the composite anomaly of the global state should be decoupled for accurate localization of the local monitored variable.
The traditional block division method is mainly carried out by adopting a data driving method, but various operation condition data samples in an actual industrial system are difficult to obtain, or the data samples are strong and incomplete, so that the block division method based on the data driving is difficult to be suitable for monitoring the production process of a modern large-scale flow.
Accordingly, there is a need for improvement and development in the art.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a monitoring method based on multi-level industrial structure knowledge block division aiming at the defects of the prior art, and aims to solve the problems that the plant-level process monitoring in the prior art is difficult to obtain various operation condition data samples in an actual industrial system or the data samples are strongly incomplete, so that the block division method based on data driving is difficult to be suitable for monitoring the modern large-scale flow production process.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect, an embodiment of the present invention provides a method for monitoring knowledge block partitioning based on a multi-level industrial structure, where the method includes:
constructing a multi-level knowledge graph of the industrial process;
performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
And obtaining a global monitoring result and a local monitoring result of the multi-level sub-blocks according to the multi-level sub-block statistical data.
In one implementation, wherein the building a multi-level knowledge graph of an industrial process comprises:
acquiring a concerned object set, a hierarchy parameter and domain expert knowledge; wherein the set of objects of interest is used to characterize the object of interest; the hierarchy comprises a business layer, an index layer, a factory-level process layer, a sub-process layer and a device layer; the hierarchy parameters comprise control parameters, system state parameters, index data and market information data;
performing entity classification and entity relationship classification on the concerned object set and the hierarchical parameters to obtain an entity classification matrix and an entity relationship classification matrix;
And obtaining a multi-level knowledge graph of the industrial process according to the entity classification matrix and the entity relationship classification matrix.
In one implementation, the multi-level sub-block statistics include a main system metric, a residual statistic;
The sub-block division is performed on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and the multi-level sub-block statistical data obtaining according to the multi-level sub-blocks comprises the following steps:
Performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
Carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
singular value decomposition is carried out on the normalized parameters to obtain a load matrix and a score matrix;
and obtaining principal component statistics and residual error statistics according to the load matrix and the score matrix.
In one implementation, the obtaining the principal component statistic and the residual statistic according to the load matrix and the score matrix includes:
obtaining principal component variables and residual variables according to the load matrix and the score matrix;
And obtaining principal component statistics and residual error statistics according to the principal component variables and the residual error variables.
In one implementation, the multi-level sub-block statistical data includes a main element statistical threshold and a residual statistical threshold, the sub-block dividing is performed on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and the obtaining the multi-level sub-block statistical data according to the multi-level sub-blocks includes:
Performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
Carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
singular value decomposition is carried out on the normalization parameters to obtain a diagonal matrix;
And obtaining a principal component statistic threshold value and a residual statistic threshold value according to the diagonal matrix.
In one implementation manner, the obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data includes:
Obtaining a global monitoring state and a local monitoring state of the multi-level sub-block according to the principal component statistic, the residual error statistic, a principal component statistic threshold value and a residual error statistic threshold value;
and obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state.
In one implementation, the obtaining the global monitoring state and the local monitoring state of the multi-level sub-block according to the principal component statistic and the residual statistic includes:
Performing index calculation on the principal component statistics and the residual error statistics to obtain a plurality of total statistics indexes and a plurality of local statistics indexes;
And obtaining the global monitoring state and the local monitoring state at a plurality of moments according to the global statistics index and the local statistics index.
In one implementation, the obtaining the global monitoring state and the local monitoring state of the multi-level sub-block according to the principal component statistic and the residual statistic further includes:
When the principal component statistic is greater than a principal component statistic threshold or the residual statistic is greater than a residual statistic threshold, calculating a tribute diagram according to the principal component statistic and the residual statistic; the contribution graph is used for representing the contribution rate of the principal element statistic and the residual statistic to the multi-level industrial structure knowledge block.
In one implementation manner, the obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state includes:
When the global monitoring state is abnormal or the local monitoring state is abnormal, determining a reason variable according to the contribution graph, wherein the reason variable is used for representing the variable quantity of the level parameter; the global monitoring state abnormality is that global principal component statistics are larger than a global principal component statistics threshold or global residual statistics are larger than a global residual statistics threshold; the local monitoring state abnormality is that local principal component statistics are larger than a local principal component statistics threshold or local residual statistics are larger than a local residual statistics threshold;
and calculating the global abnormal positioning result and the local abnormal positioning result of the reason variable by adopting an AND gate mode.
In a second aspect, an embodiment of the present invention further provides a monitoring device based on multi-level industrial structure knowledge block division, where the device includes:
The multi-level knowledge graph construction unit is used for constructing a multi-level knowledge graph of the industrial process;
The multi-level sub-block statistical data unit is used for carrying out sub-block division on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
And the global monitoring result and local monitoring result acquisition unit is used for acquiring the global monitoring result and the local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data.
In a third aspect, an embodiment of the present invention further provides an intelligent terminal, including a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors, where the one or more programs include a monitoring method for executing the multi-level industrial structure knowledge block division according to any one of the above.
In a fourth aspect, embodiments of the present invention also provide a non-transitory computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform a method of monitoring based on multi-level industrial structure knowledge block partitioning as described in any one of the above.
The invention has the beneficial effects that: the embodiment of the invention firstly constructs a multi-level knowledge graph of an industrial process; then carrying out sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold; finally, according to the multi-level sub-block statistical data, a global monitoring result and a local monitoring result of the multi-level sub-block are obtained; therefore, in the embodiment of the invention, the multi-level knowledge graph of the industrial process is constructed by using a small amount of simple expert domain knowledge, the sub-block division is performed based on the nodes of the multi-level knowledge graph, and finally the principal component statistics and the residual statistics are counted according to the multi-level sub-block, so that the accurate positioning of the abnormal nodes is realized through the contribution graph backtracking strategy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an overall technical solution provided in an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a monitoring method based on multi-level industrial structure knowledge block division according to an embodiment of the present invention.
FIG. 3 is a schematic diagram of a process for constructing a multi-level knowledge graph according to an embodiment of the invention.
FIG. 4 is a schematic diagram of another implementation of the process for constructing a multi-level knowledge graph according to an embodiment of the invention.
FIG. 5 is a diagram of a multi-level knowledge graph, provided by an embodiment of the invention.
FIG. 6 is a schematic diagram of multi-level sub-block statistic calculation and variable contribution graph according to an embodiment of the present invention.
Fig. 7 is a schematic block diagram of a monitoring device based on multi-level industrial structure knowledge block division according to an embodiment of the present invention.
Fig. 8 is a schematic block diagram of an internal structure of an intelligent terminal according to an embodiment of the present invention.
Detailed Description
The invention discloses a monitoring method, a device, an intelligent terminal and a storage medium based on multi-level industrial structure knowledge block division, which are used for making the purposes, technical schemes and effects of the invention clearer and clearer, and further detailed description of the invention is provided below by referring to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The problem that the block division method based on data driving is difficult to be suitable for monitoring the production process of a modern large-scale flow is caused by the difficulty in acquiring data samples of various operation conditions in an actual industrial system or the fact that the data samples are strongly incomplete in nature in plant-level process monitoring in the prior art.
In order to solve the problems of the prior art, the embodiment provides a monitoring method based on multi-level industrial structure knowledge block division, a multi-level knowledge graph of an industrial process is constructed by the method through a small amount of simple knowledge in the expert field, sub-block division is carried out based on nodes of the multi-level knowledge graph, principal component statistics and residual difference statistics are counted according to the multi-level sub-blocks, and accurate positioning of abnormal nodes is achieved through a contribution graph backtracking strategy.
Exemplary method
The embodiment provides a monitoring method based on multi-level industrial structure knowledge block division, which can be applied to an intelligent terminal for industrial knowledge automation. As shown in fig. 1, the method includes:
step S100, constructing a multi-level knowledge graph of an industrial process;
In the prior art, the prior actual production process has few data samples and difficult acquisition of priori knowledge, and the invention constructs a multi-level knowledge graph of the industrial process on the basis of simple expert domain knowledge, so as to prepare for reasonable block division in the follow-up process, ensure the performance of a block or scattered monitoring system, and further ensure the safety of large-scale flow industrial production. The multi-level knowledge graph is composed of a number of sheet triples (head H-relation r-tail T), where the head H and tail T can be considered physical entities or attribute values, as shown in fig. 3 (left), which can be considered as a fact characterization in a space vector, and can be clearly described by TransE embedded method, as shown in fig. 3 (right). However, there are many differences between knowledge graph construction processes for industrial processes and internet generalized knowledge graph construction processes, where data sources are both from the internet and from monitoring variables. As shown in fig. 4 (left), if the tail T is the object of interest and in fact the object can be reflected by a plurality of monitored variables (a plurality of head H nodes), then the relationship between them can be calculated from a binary symmetric adjacency (link) matrix a, which can be expressed as:
Wherein a kl represents the relationship between the kth tail node and the first head node, and it can be determined according to expert knowledge; the binary symmetrical adjacency matrix A represents the relation among a plurality of nodes in one level in the knowledge graph; matrix a represents a knowledge graph with k nodes in the nodes, and each node can be described by l variables. Similarly, each knowledge graph node is composed of one object of interest and a plurality of monitored variables, each knowledge graph has a plurality of nodes, and each level has a plurality of knowledge graph nodes, as shown in fig. 4 (right) as a two-level knowledge graph. The multi-level knowledge graph of an industrial process can be regarded as a descriptive graph, which is one of the most suitable and efficient ways to describe relationships between multiple levels, and can be extracted from metadata of a number of complex monitored variables.
In order to obtain a multi-level knowledge graph, the building of the multi-level knowledge graph of an industrial process comprises the steps of:
S101, acquiring a concerned object set, a hierarchy parameter and domain expert knowledge; wherein the set of objects of interest is used to characterize the object of interest; the hierarchy comprises a business layer, an index layer, a factory-level process layer, a sub-process layer and a device layer; the hierarchy parameters comprise control parameters, system state parameters, index data and market information data;
S102, carrying out entity classification and entity relation classification on the concerned object set and the hierarchical parameters to obtain an entity classification matrix and an entity relation classification matrix;
s103, obtaining a multi-level knowledge graph of the industrial process according to the entity classification matrix and the entity relation classification matrix.
Specifically, firstly acquiring a concerned object set, a hierarchy parameter and domain expert knowledge, wherein the concerned object set is used for representing the characteristics of the concerned object; the hierarchy comprises a business layer, an index layer, a factory-level process layer, a sub-process layer and a device layer; the hierarchy parameters comprise control parameters, system state parameters, index data and market information data; in one implementation, the method for calculating any node of the multi-level knowledge graph adopts the following formula:
Where a il represents a selected relevant monitored variable or parameter, etc., to describe an object of interest, i.e., an object of interest in an object of interest set. X i,Yv represents the features of the object of interest and the metrology observer, respectively. The above formula shows that any knowledge graph node has a large number of measurement observers, and the monitored variables between knowledge graph nodes of different levels are overlapped and coupled, so that the coupling between the variables is beneficial to maintaining. After the object of interest set, the hierarchy parameters and the domain expert knowledge are obtained, entity classification and entity relationship classification are also required to be carried out on the object of interest set and the hierarchy parameters to obtain an entity classification matrix and an entity relationship classification matrix, the named entity classification in the industrial production process mainly refers to the object of interest and related monitoring variables or parameters thereof, and the knowledge graph of each hierarchy contains a large amount of key market information, sensor measurement data, executors, raw material components, intermediate products, even intermediate statistical data and the like. In this embodiment, the set of objects of interest, the hierarchical parameters, may be physically categorized using a rule-based approach, for example: the rule-based named entity classification may be described as follows:
Wherein, X n×m is a single-component or a single-component, The related principal component statistics T 2 and residual statistics SPE of the jth level and the upper level in the ith knowledge graph node are respectively represented; /(I)Respectively representing control parameters, system state data and index data; /(I)Market information data; m i, i=1, 2,3,4,5 represents the dimension of the final feature variable. The named entity classification method based on rules in the industrial process can obtain high-precision entities, and the high-precision entities are guarantees of a high-performance multi-level knowledge graph. The difficulty of the named entity classification described above is in accurately describing the entity and marking the type of the entity. In order to obtain a higher-precision multi-level knowledge graph, the embodiment of the invention provides a "sitting-together" method, by which the object-of-interest set and the level parameters are subjected to entity relationship classification, for example: as shown in fig. 5 (a). Fig. 5 (a) depicts five nodes of interest (1, 2,3,4, 5) and their corresponding monitored variables and parameters (v 1*,v2*,v3*,v4*,v5*). If the knowledge graph of the node 5 is the object of interest, the monitoring variables and other parameters reflecting its operational status should include knowledge graphs of its adjacent upstream and downstream nodes. This means that the system specificity of node 5 can be reflected by numerous variables of nearby nodes (1, 2,3, 4) and their derivatives. The entity relationship classification matrix of the j-th level i knowledge graph can be expressed as:
Wherein, Is the binary symmetric adjacency matrix of the ith knowledge graph of the jth level; /(I)The binary adjacency matrix is constructed by principal elements or residual statistics of sub-blocks of a knowledge graph of the previous level; /(I)The relation matrix is respectively between the entity and a plurality of control parameters, the running state of the system and index parameters; /(I)Representing a matrix of relationships between the object of interest and the market information variables.
From the entity classification matrix and the entity relationship classification matrix, a multi-level knowledge graph of the industrial process can be obtained. In a factory-level mass production process, a multi-level knowledge graph can be regarded as a higher-level knowledge organization form, and the purpose of the multi-level knowledge graph can be summarized as integrating, disambiguating, verifying and updating heterogeneous data from different knowledge sources under a unified framework, and integrating information, data, methods, experience and human ideas, wherein the knowledge framework is a first key problem, and for a large-scale factory-level range, the multi-level knowledge graph comprises five levels: a business layer, an index layer, a factory level process layer, a sub-process layer and a device layer. As shown in fig. 5 (b). Fig. 5 (c) shows a calculation and construction method of any node of each level knowledge graph. In this embodiment, the monitored variables or parameters of each node in the multi-level knowledge graph overlap, which is contrary to the previous independent co-distribution assumption. This independent co-distribution assumption is critical to conventional distribution anomaly monitoring methods. The mechanism, namely the node state is influenced by the states of the upstream node and the downstream node, is more consistent with the actual situation, and provides for distributed abnormal state monitoring.
After obtaining the multi-level knowledge graph of the industrial process, the following steps may be performed as shown in fig. 1: s200, performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistical data comprises principal component statistics, residual statistics, principal component statistics threshold values and residual statistics threshold values; correspondingly, the sub-block division is performed on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and the multi-level sub-block statistical data is obtained according to the multi-level sub-blocks, which comprises the following steps:
S201, performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
S202, carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
s203, carrying out singular value decomposition on the normalized parameters to obtain a load matrix, a score matrix and a diagonal matrix;
S204, obtaining multi-level sub-block statistical data according to the load matrix, the score matrix and the diagonal matrix.
Specifically, there are three types of block partitions in the prior art: sub-block division according to the physical entity distribution of the object of interest, sub-block division based on PCA decomposition principal component, sub-block division based on operation unit, sub-block division according to the physical entity distribution of the object of interest: the plant-level distributed modeling and monitoring framework is to integrate process structures and big data knowledge to realize block division. Wherein the distribution formula comprises two layers of meanings: spatially distributed modeling and hierarchical monitoring for a plant-level process having a plurality of operating units; distributed parallel modeling of large process data with various functions. The framework divides the whole production process into a factory level, a block level and a variable level according to the spatial distribution of the data storage so as to realize the production process monitoring of the whole factory level. Wherein the block partitioning is performed in accordance with the physical entity distribution of the object of interest. Sub-block partitioning of the main component based on PCA decomposition: PCA is to find the projection direction that most represents the original data in the least mean square sense, and the k principal components selected are uncorrelated with each other. By constructing sub-blocks on each uncorrelated principal component, the diversity requirement of sub-block division can be satisfied; and selecting the most relevant variable on each irrelevant subblock, so that the precision requirement of each subblock model can be met. I.e. k +1 sub-blocks are built up together in the process data. And selecting the corresponding variable of each sub-block according to the contribution value of each variable to each main component, namely each sub-block. Similar studies have also constructed sub-block partitioning based on independent principal component analysis. Sub-block division based on operation unit: aiming at the multi-unit factory-level chemical process, a local unit monitoring model needs to be established, the running state of the local unit is monitored and analyzed, and then the whole production process is monitored. The technology can be seen that the sub-block division in the distributed monitoring system of the existing large-scale factory-level production process is based on the physical distribution, production process data and the like of the monitored object, and reasonable sub-block division is realized by expert knowledge and a data driving method. However, the defects are two: firstly, a large number of strongly complete data samples of various operation conditions are difficult to obtain by an actual industrial system; secondly, expert knowledge in an actual industrial system has strong ambiguity and uncertainty, high complexity and difficulty in quantification and transformation, and under the condition of lacking an accurate model or priori knowledge, the relevance of monitoring variables can be split by unsuitable multi-block division, so that the monitoring performance is reduced. In the embodiment of the invention, the nodes in the multi-level knowledge graph are sub-partitioned to obtain multi-level sub-blocks, and in practice, each node in the multi-level knowledge graph is used as a block node, and the multi-level knowledge graph is partitioned to obtain the multi-level sub-blocks. The distributed monitoring system with multi-sub-block division repeatedly divides a large number of monitoring variables into several sub-blocks, and then builds a monitoring model for each sub-block to mine more process information, thereby improving the monitoring effect. After a multi-level sub-block is obtained, carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters; singular value decomposition is carried out on the normalized parameters to obtain a load matrix, a score matrix and a diagonal matrix; for example, the load matrix, the score matrix, and the diagonal matrix are calculated by the following calculation formulas:
T＝XP，/>
Where Λ=diag (λ i,λi (i=1, 2,.., m)) is a diagonal matrix of each singular value. T is the scoring matrix and P is the loading matrix.
And then obtaining multi-level sub-block statistical data according to the load matrix, the score matrix and the diagonal matrix. Correspondingly, the step of obtaining multi-level sub-block statistical data according to the load matrix, the score matrix and the diagonal matrix comprises the following steps: obtaining principal component variables and residual variables according to the load matrix and the score matrix; obtaining principal component statistics and residual statistics according to the principal component variables and the residual variables; and obtaining a principal component statistic threshold value and a residual statistic threshold value according to the diagonal matrix.
Specifically, according to the load matrix and the score matrix, principal component variables and residual variable are obtained; for example: decomposing the residual variable into principal component variables and residual variables by adopting principal component analysis technology:
Wherein, T epsilon R m×κ,P∈Rm×κ are respectively a principal component score matrix and a corresponding load matrix; respectively representing a residual score matrix and a corresponding load matrix; e ε R n×m represents the residual matrix. k.ltoreq.m represents the number of principal elements, the value of which can be determined by the Cumulative Principal Variance (CPV) PRINCIPAL VARIANCE. And obtaining principal component statistics T 2 and residual statistics SPE according to the principal component variables and the residual variables:
Where t=xp represents the score vector of sample x; e=x-tP T denotes the residual vector of sample x. And obtaining a principal component statistic threshold value and a residual statistic threshold value according to the diagonal matrix, for example: the diagonal matrix is Λ=diag (λ i,λi (i=1, 2,., m)), from which can be derived H 0＝1-2θ1θ3/3θ1 2, k is less than or equal to m and represents the number of principal elements, and the principal element statistic threshold and the residual statistic threshold are expressed as follows:
Wherein F κ,m-κ：α represents F distribution critical values with kappa and m-kappa degrees of freedom and confidence level alpha; c α denotes the threshold at which the standard is globally distributed at the confidence level α.
After obtaining the multi-level sub-block statistics, the following steps may be performed as shown in fig. 1: and step S300, obtaining a global monitoring result and a local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data. Correspondingly, in order to obtain the global monitoring result and the local monitoring result of the multi-level sub-block, the obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data includes the following steps:
S301, obtaining a global monitoring state and a local monitoring state of the multi-level sub-block according to the principal component statistic, the residual statistic, a principal component statistic threshold value and a residual statistic threshold value;
S302, obtaining a global monitoring result and a local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state.
Specifically, a global monitoring state and a local monitoring state of the multi-level sub-block are obtained according to the principal component statistic, the residual statistic, a principal component statistic threshold value and a residual statistic threshold value; correspondingly, the obtaining the global monitoring state and the local monitoring state of the multi-level sub-block according to the principal component statistic and the residual statistic comprises the following steps: performing index calculation on the principal component statistics and the residual statistics to obtain a plurality of global statistics indexes and a plurality of local statistics indexes; and obtaining global monitoring states and local monitoring states at a plurality of moments according to the global statistics index and the local statistics index.
Specifically, as shown in fig. 6, the main statistics and the residual statistics of nodes in two adjacent hierarchical sub-blocks are used as monitoring variables, and the PCA technology, independent principal component ICA analysis, partial least squares analysis PLS, typical correlation analysis CCA and other technologies are adopted to calculate four global statistical indexesAs shown in fig. 4, the four statistical indexes are the principal component statistical index of the principal component variable, the residual error statistical index of the principal component variable, the principal component statistical index of the residual error variable, and the residual error statistical index of the residual error variable of the principal component score matrix, respectively. In addition, two local statistical indexes { T 2, SPE } can be obtained, and then a global monitoring state and a local monitoring state at a plurality of moments are obtained according to the global statistical index and the local statistical index. For example, global and local conditions may monitor conditions resulting in four situations: (1) a global monitorable state and a local monitorable state: any four global statistics are greater than the threshold of the corresponding statistics, while any two local statistics are greater than the threshold of the corresponding statistics; (2) global monitorable state and local non-monitorable state: any four global statistics are greater than the threshold of the corresponding statistics, while any two local statistics are not greater than the threshold of the corresponding statistics; (3) globally non-monitorable state and locally monitorable state: any four global statistics are not greater than the threshold of the corresponding statistics, while any two local statistics are greater than the threshold of the corresponding statistics; (4) Global unmonitored state and local unmonitored state: any four global statistic is not greater than the threshold of the corresponding statistic, while any two local statistic is not greater than the threshold of the corresponding statistic. Furthermore, if the global or local statistic is greater than the threshold of the corresponding statistics, a contribution graph is calculated from the principal statistic and the residual statistic, for example, each monitored variable or parameter contribution graph is calculated, as follows:
Wherein, Respectively representing a contribution graph of principal component statistics T 2 and residual statistics SPE; D=p TΛP,ξi represents the eigenvalues of the ith column of the identity matrix I m.
And after the global monitoring state and the local monitoring state of the multi-level sub-block are obtained, obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state. Correspondingly, the obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state comprises the following steps: when the global monitoring state is abnormal or the local monitoring state is abnormal, determining a reason variable according to the tribute diagram, wherein the reason variable is used for representing a variable of a level parameter; the global monitoring state abnormality is that global principal component statistics are larger than a global principal component statistics threshold or global residual statistics are larger than a global residual statistics threshold; the local monitoring state abnormality is that local principal component statistics are larger than a local principal component statistics threshold or local residual statistics are larger than a local residual statistics threshold; and calculating the global abnormal positioning result and the local abnormal positioning result of the reason variable by adopting an AND gate mode.
Specifically, firstly, when the global monitoring state is abnormal or the local monitoring state is abnormal, determining a reason variable according to the contribution graph, wherein the reason variable is used for representing a variable of a layer level parameter; the global monitoring state abnormality is that global principal component statistics are larger than a global principal component statistics threshold or global residual statistics are larger than a global residual statistics threshold; the local monitoring state anomaly is that local principal component statistics are larger than local principal component statistics threshold or local residual statistics are larger than local residual statistics threshold, for example, when an anomaly with unknown prior knowledge occurs, a variable or parameter with larger contribution rate can be used as a source dependent variable. And then calculating the global abnormal positioning result and the local abnormal positioning result of the reason variable by adopting an AND gate mode. For example, due to the multiple levels involved, when the final monitored variable is reached, there is a large difference in the results of each monitored variable at different levels, even if the results conflict. For this reason, the present embodiment adopts the and gate policy to realize the positioning of the abnormal state.
Wherein R p represents an abnormal positioning result; Representing the positioning result of the abnormal reason of the ith node; /(I) Representing the abnormal result corresponding to the variable with larger contribution graph of each level after the occurrence of the abnormality of the ith node, if/>A value of 0 indicates no occurrence of anomaly at any level,/>A1 indicates that at least one level shows that an anomaly has occurred and that it is necessary to trace back to this variable.
Exemplary apparatus
As shown in fig. 7, an embodiment of the present invention provides a monitoring apparatus based on multi-level industrial structure knowledge block division, which includes a multi-level knowledge graph construction unit 401, a multi-level sub-block statistical data unit 402, a global monitoring result and local monitoring result obtaining unit 403, wherein:
a multi-level knowledge graph construction unit 401 for constructing a multi-level knowledge graph of an industrial process;
A multi-level sub-block statistical data unit 402, configured to sub-block divide nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtain multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
The global monitoring result and local monitoring result obtaining unit 403 is configured to obtain a global monitoring result and a local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data.
The present embodiment constructs a multi-level knowledge graph of an industrial process by a multi-level knowledge graph construction unit 401; then, sub-block division is carried out on nodes in the multi-level knowledge graph through a multi-level sub-block statistical data unit 402 to obtain multi-level sub-blocks, and multi-level sub-block statistical data are obtained according to the multi-level sub-blocks; finally, the global monitoring result and the local monitoring result of the multi-level sub-block are obtained by the global monitoring result and local monitoring result obtaining unit 403 according to the multi-level sub-block statistical data. The modules are used for constructing a multi-level knowledge graph of an industrial process by using a small amount of simple expert domain knowledge, sub-block division is carried out by taking the nodes of the multi-level knowledge graph as the basis, and finally, principal element statistics and residual statistics are counted according to the multi-level sub-blocks, so that the accurate positioning of abnormal nodes is realized by a contribution graph backtracking strategy.
Based on the above embodiment, the present invention further provides an intelligent terminal, and a functional block diagram thereof may be shown in fig. 8. The intelligent terminal comprises a processor, a memory, a network interface, a display screen and a temperature sensor which are connected through a system bus. The processor of the intelligent terminal is used for providing computing and control capabilities. The memory of the intelligent terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the intelligent terminal is used for communicating with an external terminal through network connection. The computer program, when executed by a processor, implements a method of monitoring knowledge block partitioning based on a multi-level industrial structure. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor of the intelligent terminal is arranged in the intelligent terminal in advance and is used for monitoring the running temperature of internal equipment.
It will be appreciated by those skilled in the art that the schematic diagram in fig. 8 is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation of the smart terminal to which the present invention is applied, and that a specific smart terminal may include more or less components than those shown in the drawings, or may combine some components, or have a different arrangement of components.
In one embodiment, a smart terminal is provided that includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
constructing a multi-level knowledge graph of the industrial process;
performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
And obtaining a global monitoring result and a local monitoring result of the multi-level sub-blocks according to the multi-level sub-block statistical data.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
In summary, the invention discloses a monitoring method, a device, an intelligent terminal and a storage medium based on multi-level industrial structure knowledge block division, wherein the method comprises the following steps: constructing a multi-level knowledge graph of the industrial process; performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; the multi-level sub-block statistical data comprises principal component statistics, residual statistics, a principal component statistics threshold and a residual statistics threshold; and obtaining global monitoring results and local monitoring results of the multi-level sub-blocks according to the multi-level sub-block statistical data. According to the embodiment of the invention, through the method, a multi-level knowledge graph of an industrial process is constructed by using a small amount of simple expert domain knowledge, sub-block division is carried out by taking the nodes of the multi-level knowledge graph as the basis, and finally, principal element statistics and residual statistics are counted according to the multi-level sub-blocks, so that the accurate positioning of abnormal nodes is realized through a contribution graph backtracking strategy.
Based on the above embodiments, the present invention discloses a method for monitoring knowledge block division based on multi-level industrial structure, it should be understood that the application of the present invention is not limited to the above examples, and those skilled in the art can make modifications or changes according to the above description, and all such modifications and changes should fall within the scope of the appended claims.
Claims (10)
1. A method for monitoring knowledge block partitioning based on a multi-level industrial structure, the method comprising:
constructing a multi-level knowledge graph of the industrial process;
performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
according to the multi-level sub-block statistical data, a global monitoring result and a local monitoring result of the multi-level sub-block are obtained;
the building a multi-level knowledge graph of an industrial process includes:
Acquiring a concerned object set, a hierarchy parameter and domain expert knowledge; wherein the set of objects of interest is used to characterize the object of interest; the hierarchy comprises a business layer, an index layer, a factory-level process layer, a sub-process layer and a device layer; the hierarchy parameters comprise control parameters, system state parameters, index data and market information data;
Performing entity classification and entity relationship classification on the concerned object set and the hierarchical parameters to obtain an entity classification matrix and an entity relationship classification matrix;
Obtaining a multi-level knowledge graph of the industrial process according to the entity classification matrix and the entity relationship classification matrix;
The multi-level sub-block statistical data comprises principal element statistics and residual statistics;
the sub-block division is performed on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and the multi-level sub-block statistical data obtaining according to the multi-level sub-blocks comprises the following steps:
Performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
singular value decomposition is carried out on the normalized parameters to obtain a load matrix and a score matrix;
and obtaining principal component statistics and residual statistics according to the load matrix and the score matrix.
2. The method for monitoring knowledge block partitioning based on multi-level industrial structure according to claim 1, wherein obtaining principal component statistics and residual statistics from the load matrix and the score matrix comprises:
obtaining principal component variables and residual variables according to the load matrix and the score matrix;
And obtaining principal component statistics and residual statistics according to the principal component variables and the residual variables.
3. The method for monitoring knowledge block partitioning based on a multi-level industrial structure according to claim 1, wherein the multi-level sub-block statistics comprise a principal component statistics threshold and a residual statistics threshold, the sub-block partitioning is performed on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and the obtaining multi-level sub-block statistics according to the multi-level sub-blocks comprises:
Performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
singular value decomposition is carried out on the normalization parameters to obtain a diagonal matrix;
And obtaining a principal component statistic threshold value and a residual statistic threshold value according to the diagonal matrix.
4. The method for monitoring knowledge block partitioning based on multi-level industrial structure according to claim 3, wherein obtaining global monitoring results and local monitoring results of multi-level sub-blocks according to the multi-level sub-block statistical data comprises:
obtaining a global monitoring state and a local monitoring state of the multi-level sub-block according to the principal component statistic, the residual error statistic, a principal component statistic threshold value and a residual error statistic threshold value;
And obtaining the global monitoring result and the local monitoring result of the multi-level sub-block according to the global monitoring state and the local monitoring state.
5. The method of claim 4, wherein obtaining global monitoring states and local monitoring states of the multi-level sub-blocks based on the principal component statistics and the residual statistics comprises:
Performing index calculation on the principal component statistics and the residual error statistics to obtain a plurality of global statistics indexes and a plurality of local statistics indexes;
And obtaining global monitoring states and local monitoring states at a plurality of moments according to the global statistics index and the local statistics index.
6. The method of claim 5, wherein obtaining global monitoring states and local monitoring states of multi-level sub-blocks from the principal component statistics and the residual statistics further comprises:
Calculating a contribution graph according to the principal component statistic and the residual statistic when the principal component statistic is greater than a principal component statistic threshold or the residual statistic is greater than a residual statistic threshold; the contribution graph is used for representing the contribution rate of the principal element statistic and the residual statistic to the multi-level industrial structure knowledge block.
7. The method for monitoring knowledge block partitioning based on multi-level industrial structure according to claim 6, wherein obtaining a global monitoring result and a local monitoring result of a multi-level sub-block according to the global monitoring state and the local monitoring state comprises:
When the global monitoring state is abnormal or the local monitoring state is abnormal, determining a reason variable according to the contribution graph, wherein the reason variable is used for representing the variable of the level parameter; the global monitoring state abnormality is that global principal component statistics are larger than a global principal component statistics threshold or global residual statistics are larger than a global residual statistics threshold; the local monitoring state abnormality is that local principal component statistics are larger than a local principal component statistics threshold or local residual statistics are larger than a local residual statistics threshold;
And calculating the global abnormal positioning result and the local abnormal positioning result of the reason variable by adopting an AND gate mode.
8. A monitoring device based on multi-level industrial structure knowledge block partitioning, the device comprising:
The multi-level knowledge graph construction unit is used for constructing a multi-level knowledge graph of the industrial process;
The multi-level sub-block statistical data unit is used for carrying out sub-block division on the nodes in the multi-level knowledge graph to obtain multi-level sub-blocks, and obtaining multi-level sub-block statistical data according to the multi-level sub-blocks; wherein the multi-level sub-block statistics include principal component statistics, residual statistics, principal component statistics threshold and residual statistics threshold;
The global monitoring result and local monitoring result acquisition unit is used for acquiring the global monitoring result and the local monitoring result of the multi-level sub-block according to the multi-level sub-block statistical data;
The multi-level knowledge building unit is further configured to:
Acquiring a concerned object set, a hierarchy parameter and domain expert knowledge; wherein the set of objects of interest is used to characterize the object of interest; the hierarchy comprises a business layer, an index layer, a factory-level process layer, a sub-process layer and a device layer; the hierarchy parameters comprise control parameters, system state parameters, index data and market information data;
Performing entity classification and entity relationship classification on the concerned object set and the hierarchical parameters to obtain an entity classification matrix and an entity relationship classification matrix;
Obtaining a multi-level knowledge graph of the industrial process according to the entity classification matrix and the entity relationship classification matrix;
The multi-level sub-block statistical data comprises principal element statistics and residual statistics;
the multi-level sub-block statistics unit is further for:
Performing sub-block division on nodes in the multi-level knowledge graph to obtain multi-level sub-blocks;
carrying out normalization calculation on the entity classification matrix in the multi-level sub-block to obtain normalization parameters;
singular value decomposition is carried out on the normalized parameters to obtain a load matrix and a score matrix;
and obtaining principal component statistics and residual statistics according to the load matrix and the score matrix.
9. An intelligent terminal comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for performing the method of any of claims 1-7.
10. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110393994.8A CN113239187B (en) | 2021-04-13 | 2021-04-13 | Monitoring method based on multi-level industrial structure knowledge block division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110393994.8A CN113239187B (en) | 2021-04-13 | 2021-04-13 | Monitoring method based on multi-level industrial structure knowledge block division |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113239187A CN113239187A (en) | 2021-08-10 |
| CN113239187B true CN113239187B (en) | 2024-05-14 |
Family
ID=77127996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110393994.8A Active CN113239187B (en) | 2021-04-13 | 2021-04-13 | Monitoring method based on multi-level industrial structure knowledge block division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113239187B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115307669B (en) * | 2022-10-11 | 2023-01-10 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus, and medium for detecting abnormal sensor of system under test |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012090492A1 (en) * | 2010-12-28 | 2012-07-05 | 株式会社 東芝 | Process monitoring and diagnosis system |
| CN102880151A (en) * | 2012-10-11 | 2013-01-16 | 浙江大学 | Double-layer data model-driven plant-level chemical process monitoring method |
| CN103389701A (en) * | 2013-07-15 | 2013-11-13 | 浙江大学 | Plant-level process fault detection and diagnosis method based on distributed data model |
| CN105893700A (en) * | 2016-04-26 | 2016-08-24 | 陆新建 | Chemical production on-line fault detection and diagnosis technique based on physical-large data hybrid model |
| CN108762228A (en) * | 2018-05-25 | 2018-11-06 | 江南大学 | A kind of multi-state fault monitoring method based on distributed PCA |
| CN109507972A (en) * | 2018-12-19 | 2019-03-22 | 中国计量大学 | Industrial processes fault monitoring method based on layer-stepping non-gaussian monitoring algorithm |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0007063D0 (en) * | 2000-03-23 | 2000-05-10 | Simsci Limited | Mulitvariate statistical process monitors |
| US8065247B2 (en) * | 2007-11-21 | 2011-11-22 | Inomaly, Inc. | Systems and methods for multivariate influence analysis of heterogenous mixtures of categorical and continuous data |
| US8352216B2 (en) * | 2008-05-29 | 2013-01-08 | General Electric Company | System and method for advanced condition monitoring of an asset system |
| EP3404593A1 (en) * | 2017-05-15 | 2018-11-21 | Tata Consultancy Services Limited | Method and system for data based optimization of performance indicators in process and manufacturing industries |
-
2021
- 2021-04-13 CN CN202110393994.8A patent/CN113239187B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012090492A1 (en) * | 2010-12-28 | 2012-07-05 | 株式会社 東芝 | Process monitoring and diagnosis system |
| CN102880151A (en) * | 2012-10-11 | 2013-01-16 | 浙江大学 | Double-layer data model-driven plant-level chemical process monitoring method |
| CN103389701A (en) * | 2013-07-15 | 2013-11-13 | 浙江大学 | Plant-level process fault detection and diagnosis method based on distributed data model |
| CN105893700A (en) * | 2016-04-26 | 2016-08-24 | 陆新建 | Chemical production on-line fault detection and diagnosis technique based on physical-large data hybrid model |
| CN108762228A (en) * | 2018-05-25 | 2018-11-06 | 江南大学 | A kind of multi-state fault monitoring method based on distributed PCA |
| CN109507972A (en) * | 2018-12-19 | 2019-03-22 | 中国计量大学 | Industrial processes fault monitoring method based on layer-stepping non-gaussian monitoring algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113239187A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao | Perspectives on nonstationary process monitoring in the era of industrial artificial intelligence | |
| Yu et al. | A novel hybrid of auto-associative kernel regression and dynamic independent component analysis for fault detection in nonlinear multimode processes | |
| Zhu et al. | Information concentrated variational auto-encoder for quality-related nonlinear process monitoring | |
| Shi | In-process quality improvement: Concepts, methodologies, and applications | |
| Lou et al. | Bayesian network based on an adaptive threshold scheme for fault detection and classification | |
| CN109871002B (en) | Concurrent abnormal state identification and positioning system based on tensor label learning | |
| CN113239187B (en) | Monitoring method based on multi-level industrial structure knowledge block division | |
| Li et al. | Nonlinear dynamic process monitoring using deep dynamic principal component analysis | |
| Mosin | Machine learning and data mining methods in testing and diagnostics of analog and mixed-signal integrated circuits: Case study | |
| Irani et al. | A data-driven approach for fault diagnosis in multi-zone HVAC systems: Deep neural bilinear Koopman parity | |
| Solomentsev et al. | Diagnostics programs efficiency analysis in operation system of radioelectronic eguipment | |
| Yu et al. | An Unsupervised Fault Detection and Diagnosis With Distribution Dissimilarity and Lasso Penalty | |
| Zhou et al. | Performance evaluation method for network monitoring based on separable temporal exponential random graph models with application to the study of autocorrelation effects | |
| Ran et al. | Determining structural identifiability of parameter learning machines | |
| Yan et al. | A variable‐selection control chart via penalized likelihood and Gaussian mixture model for multimodal and high‐dimensional processes | |
| He et al. | Consistent Kalman filters for nonlinear uncertain systems over sensor networks | |
| Shi | Data fusion for in-process quality improvement | |
| Manikanta | Evaluation of modified PLS regression method to fill the missing values in training dataset | |
| Zhang et al. | Key fault propagation path identification of CNC machine tools based on maximum occurrence probability | |
| Jauhri et al. | Outlier detection for large scale manufacturing processes | |
| Gaugel et al. | Data-driven multi-objective optimization of hydraulic pump test cycles via wrapper feature selection | |
| Li et al. | A novel monitoring method based on multi-model information extraction and fusion | |
| Jia et al. | Process monitoring based on the multiblock rolling pin vine copula | |
| Oh et al. | LSTM-based PdM Platform for Automobile SCU Inspection Equipment | |
| Sittón-Candanedo et al. | Fault predictive model for HVAC Systems in the context of Industry 4.0 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |