Zinc hydrometallurgy control method, device and equipment based on mapping knowledge domain and medium

Abstract

The invention discloses a zinc hydrometallurgy control method and device based on a knowledge graph, equipment and a medium, and relates to the technical field of data processing. The method comprises the following steps: collecting process processing data of a mud-producing ion unit of zinc hydrometallurgy; constructing a zinc hydrometallurgy knowledge graph according to the process processing data on the basis of zinc hydrometallurgy process knowledge and an ionic reaction mechanism; and a regulation and control rule is extracted from the zinc hydrometallurgy knowledge graph according to a preset regulation and control target, and the zinc hydrometallurgy production process is adjusted according to the regulation and control rule. Thus, the knowledge graph is constructed according to the process processing data of the zinc hydrometallurgy mud production ion unit, the regulation and control rule is extracted based on the knowledge graph to regulate and control the zinc hydrometallurgy production process, and intelligent coordinated regulation and control of the mud production ions in the whole zinc hydrometallurgy process can be achieved through the incidence relation of the knowledge graph. Therefore, the zinc smelting production technology level is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a knowledge graph-based hydrometallurgical zinc smelting control method, device, equipment and medium. Background Art

[0002] There are many sludge-producing units in hydrometallurgy and the reactions are complex, and it is difficult to fully capture the ion data and information of the entire process space. At present, the hydrometallurgy process mainly uses manual sampling to analyze the product content and ion concentration, which has problems such as large human limitations and low efficiency. Summary of the invention

[0003] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and provide a hydrometallurgical zinc smelting control method, device, equipment and medium based on a knowledge graph, which is used to structure the process processing data of the mud ion producing unit to construct a network structure of the hydrometallurgical zinc smelting knowledge graph, and then extract control rules based on the hydrometallurgical zinc smelting knowledge graph, so as to adjust the actual production process of hydrometallurgical zinc smelting according to the control rules.

[0004] The present invention provides the following technical solutions:

[0005] In a first aspect, the present invention proposes a method for controlling hydrometallurgy of zinc based on a knowledge graph, comprising:

[0006] Collect process data of the sludge ion production unit of hydrometallurgical zinc smelting;

[0007] Based on the process knowledge and ion reaction mechanism of hydrometallurgy, a knowledge graph of hydrometallurgy is constructed according to the process processing data;

[0008] According to preset control objectives, control rules are extracted from the hydrometallurgical zinc smelting knowledge graph, and the hydrometallurgical zinc smelting production process is adjusted according to the control rules.

[0009] In one embodiment, the process knowledge and ion reaction mechanism of hydrometallurgy are based on the process data to construct a knowledge graph of hydrometallurgy, including:

[0010] Extracting knowledge from the process data based on the process knowledge and the ion reaction mechanism to obtain structured information;

[0011] The structured information is fused with knowledge, and the fused structured information is processed with knowledge based on the ontology definition and the triple definition to obtain the knowledge graph of hydrometallurgy.

[0012] In one embodiment, the extracting knowledge from the process data based on the process knowledge and the ion reaction mechanism to obtain structured information includes:

[0013] Based on the process knowledge and the ion reaction mechanism, ion reaction information and process information are extracted from the process processing data, and multiple entities and their corresponding attributes, as well as the relationship between the entities are extracted according to the ion reaction information and the process information;

[0014] The structured information is determined according to the multiple entities and their corresponding attributes, and the relationship between the entities.

[0015] In one embodiment, the knowledge processing of the fused structured information based on the ontology definition and the triple definition to obtain the hydrometallurgical zinc smelting knowledge graph includes:

[0016] Determining entities in a parallel relationship based on the similarities between the entities, and identifying entities in a hierarchical relationship based on the process data;

[0017] Generate a structured ontology according to the entities belonging to the parallel relationship and the entities belonging to the hierarchical relationship;

[0018] Extracting triples from the fused structured information;

[0019] Based on the ontology definition and the triple definition, the structured ontology and the triple are merged to obtain a new triple;

[0020] The knowledge graph of hydrometallurgy is constructed according to the new triples.

[0021] In one embodiment, the method further comprises:

[0022] New process data is acquired according to a preset time interval, and the knowledge graph of hydrometallurgy is adjusted according to the new process data.

[0023] In one embodiment, the extracting control rules from the hydrometallurgical zinc smelting knowledge graph according to the preset control target includes:

[0024] Extracting key data corresponding to the preset control target from the hydrometallurgical zinc smelting knowledge graph;

[0025] The key data are analyzed to obtain the control rules.

[0026] In one embodiment, adjusting the hydrometallurgical zinc production process according to the regulation rule comprises:

[0027] Predicting the production control result corresponding to the control rule to obtain a prediction result, wherein the prediction result includes zinc smelting parameters;

[0028] If the prediction result meets the preset control target, the hydrometallurgical zinc smelting production process is adjusted according to the control rules.

[0029] In a second aspect, the present invention proposes a knowledge graph-based hydrometallurgical zinc smelting control device, comprising:

[0030] The acquisition module is used to collect the process data of the sludge ion production unit of hydrometallurgy;

[0031] A construction module for constructing a knowledge graph of hydrometallurgy based on process knowledge and ion reaction mechanism of hydrometallurgy according to the process processing data;

[0032] A control module is used to extract control rules from the hydrometallurgical zinc smelting knowledge graph and adjust the hydrometallurgical zinc smelting production process according to the control rules.

[0033] In a third aspect, the present invention proposes a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the knowledge graph-based hydrometallurgical zinc smelting control method as described in the first aspect is implemented.

[0034] In a fourth aspect, the present invention proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the knowledge graph-based hydrometallurgical zinc smelting control method as described in the first aspect.

[0035] The knowledge graph-based hydrometallurgical zinc smelting control method, device, equipment and medium disclosed in the present invention collect process processing data of the slime ion unit of hydrometallurgical zinc smelting; based on the process knowledge and ion reaction mechanism of hydrometallurgical zinc smelting, a knowledge graph of hydrometallurgical zinc smelting is constructed according to the process processing data; according to the preset control target, control rules are extracted from the knowledge graph of hydrometallurgical zinc smelting, and the production process of hydrometallurgical zinc smelting is adjusted according to the control rules. In this way, the knowledge graph is constructed according to the process processing data of the slime ion unit of hydrometallurgical zinc smelting, and the control rules are extracted based on the knowledge graph to control the production process of hydrometallurgical zinc smelting. The intelligent coordinated control of the slime ions produced in the whole process of hydrometallurgical zinc smelting can be realized through the association relationship of the knowledge graph, thereby improving the technical level of zinc smelting production. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope of protection of the present invention. In each of the drawings, similar components are numbered similarly.

[0037] Figure 1 A schematic diagram of a process of a knowledge graph-based control method for hydrometallurgy of zinc proposed in this embodiment is shown;

[0038] Figure 2 Another schematic diagram of the process of the knowledge graph-based control method for hydrometallurgy of zinc proposed in this embodiment is shown;

[0039] Figure 3 Another schematic diagram of the process of the knowledge graph-based hydrometallurgical zinc smelting control method proposed in this embodiment is shown;

[0040] Figure 4 A structural schematic diagram of a knowledge graph-based hydrometallurgical zinc smelting control device proposed in this embodiment is shown.

[0041] Description of the accompanying drawings: 400 - hydrometallurgical zinc smelting control device based on knowledge graph; 401 - acquisition module; 402 - construction module; 403 - control module. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0043] The components of the embodiments of the present invention generally described and shown in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0044] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present invention, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0045] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0046] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present invention belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present invention.

[0047] Example 1

[0048] The disclosed embodiment provides a knowledge graph-based control method for hydrometallurgy. The method is used to perform structured processing on process processing data of a sludge ion producing unit to construct a network structure of a knowledge graph for hydrometallurgy. The control rules are then extracted based on the knowledge graph for hydrometallurgy. The actual production process of hydrometallurgy is adjusted according to the control rules.

[0049] See also Figure 1 The knowledge graph-based hydrometallurgical zinc smelting control method includes steps S101 to S103, and each step is described in detail below.

[0050] Step S101, collecting process data of the sludge ion producing unit of hydrometallurgy of zinc.

[0051] In this embodiment, real-time or historical process data of a specific link in the hydrometallurgical zinc smelting process, the sludge ion unit, is collected. These data may include, but are not limited to, key parameters such as raw material composition, reaction temperature, pressure, pH value, ion concentration, precipitate generation, and energy consumption. These data are the basis for subsequent analysis and optimization, and are crucial for understanding the dynamic changes and potential problems in the production process.

[0052] Step S102, based on the process knowledge and ion reaction mechanism of hydrometallurgy, construct a knowledge graph of hydrometallurgy according to the process processing data.

[0053] In this embodiment, the knowledge graph is a structured knowledge representation method that can display complex information in a graphical manner for easy understanding and analysis. This embodiment uses process knowledge, ion reaction mechanism and process processing data in the field of hydrometallurgical zinc smelting to construct a hydrometallurgical zinc smelting knowledge graph that reflects the relationship between various factors in the process of hydrometallurgical zinc smelting.

[0054] Step S103, extracting control rules from the hydrometallurgical zinc smelting knowledge graph according to preset control targets, and adjusting the hydrometallurgical zinc smelting production process according to the control rules.

[0055] In this embodiment, after constructing the knowledge graph of hydrometallurgy, preset control targets can be set according to their own production goals and needs (such as increasing output, reducing costs, reducing pollution, etc.). Then, the information in the knowledge graph of hydrometallurgy is used to extract the control rules required to achieve these preset control targets. These rules may involve adjusting the raw material ratio, changing the reaction conditions (such as temperature, pressure, pH value), optimizing equipment operation, etc. Finally, the hydrometallurgy production process is adjusted in real time or regularly according to these control rules to achieve the preset control targets. In this way, by collecting process processing data in actual production, combining domain expertise to build a knowledge graph, and then extracting control rules based on the knowledge graph and applying them to production practice, the intelligence level and production efficiency of the hydrometallurgy process can be significantly improved.

[0056] See also Figure 2 In a specific embodiment, step S102 includes steps S1021 to S1022, and each step is described in detail below.

[0057] Step S1021: extracting knowledge from the process data based on the process knowledge and the ion reaction mechanism to obtain structured information.

[0058] In this embodiment, knowledge extraction is the process of extracting structured information such as entities, relationships, and entity attributes from unstructured or semi-structured process data. In hydrometallurgy, it is usually necessary to parse and convert various parameters, indicators, experimental results, etc. in the zinc production process to form a format that is easy to query and understand.

[0059] Step S1022, performing knowledge fusion on the structured information, and performing knowledge processing on the fused structured information based on the ontology definition and the triple definition, so as to obtain the hydrometallurgical zinc smelting knowledge graph.

[0060] In this embodiment, due to the wide range of data sources in the knowledge graph of hydrometallurgy, there are problems such as uneven knowledge quality, repeated knowledge from different data sources, data sources may not be the same in the description of entities, no connection is established, there may be partial redundancy or contradiction, and the relationship between knowledge is not clear enough, so knowledge fusion must be carried out. For example, ZnSO4 (or the expression "zinc sulfate") in the reaction formulas of different processes must use a unified identifier, and the attribute information must be unified, such as concentration, and the concentration information is merged to obtain a complete record, so that data from different metal ion data sources can be integrated, disambiguated, processed, reasoned and verified, updated, etc. under the same framework specification, so as to achieve the integration of data, information, methods, and experience, and provide a basis for the formation of a high-quality ion network knowledge base.

[0061] At the same time, the collected process data is deleted for duplicate data, corrected for erroneous data, filled for missing data, and converted into a unified format, and the data is standardized and normalized for subsequent analysis. In terms of data storage, the Neo4j graph database is used for storage, and the security and backup mechanism of data storage are ensured.

[0062] Furthermore, according to the ontology definition and triple representation, the fused structured information is organized into a knowledge graph of hydrometallurgy with hierarchical structure and semantic relationship. This graph not only reflects the physical and chemical processes in the hydrometallurgy process, but also contains rich contextual information and logical reasoning capabilities, providing support for subsequent query, analysis and decision-making.

[0063] In a specific embodiment, the knowledge extraction of the process processing data based on the process knowledge and the ion reaction mechanism is performed to obtain structured information, including: extracting ion reaction information and process information from the process processing data based on the process knowledge and the ion reaction mechanism, and extracting multiple entities and their corresponding attributes, as well as the relationship between each of the entities based on the ion reaction information and the process information; determining the structured information based on the multiple entities and their corresponding attributes, as well as the relationship between each of the entities.

[0064] In this embodiment, the process knowledge and ion reaction mechanism of hydrometallurgy are used as guidance to screen out information related to these knowledge and mechanisms from the process processing data. This information includes, but is not limited to, ion reaction information and process information. Among them, the ion reaction information involves specific data of the generation, conversion, precipitation and other processes of ions in the solution and the content data of the main metals, such as ion concentration changes, reaction rates, ion balance under reaction conditions (such as temperature, pH value), etc.; process information involves describing the operating conditions, equipment status, raw material ratios, product characteristics, reaction time, stirring rate, pressure, current, material contact time, concentration of added substances and other information of each step in the hydrometallurgy process. At the same time, it is also necessary to obtain information such as reaction type (decomposition, electrolysis, hydrolysis, oxidation, etc.). These chemical substances, chemical formulas, reaction conditions, reaction phenomena, substance types, reaction types, and reaction equations are all used as nodes in the atlas.

[0065] Furthermore, multiple entities and their attributes are extracted from various ion reaction information and process information. In the process of hydrometallurgical zinc smelting, entities can be chemical substances such as Zn2+, SO42-, H2SO4 and other ions or compounds, or reaction conditions, reaction types, equipment, process flow, etc. When chemical substances are entities, chemical properties are used as their attributes, and various chemical reactions are regarded as relationships.

[0066] It should be noted that there are three methods for entity extraction: rule-based, statistical machine learning-based (conditional random field CRF, support vector base SVM, hidden Markov model HMM) and deep learning-based (long short-term memory network LSTM, bidirectional long short-term memory network BiLSTM-CRF, pre-trained language model based on Transformer architecture) extraction methods. One method of extracting these attributes is to use the data in the zinc smelting production operation as a training set that can be used for attribute extraction, and then apply the model to entity attribute extraction in the open domain. For relationship extraction, in order to obtain semantic information, it is also necessary to extract the association relationship between entities from the relevant corpus, and connect the entities through the relationship to form a network knowledge structure. A relationship is an edge connecting two entities, indicating a certain association or interaction between them. For example: Zn2+--(substitution generation)-->Zn means that zinc ions are generated by substitution (electrolysis) reaction. The relationship goal is to solve the problem of semantic links between ionic entities. Relation extraction mainly identifies entity relationships by artificially constructing semantic rules and templates; machine learning and deep learning can also be performed through a large amount of annotated data, which includes text and corresponding entities and relationships, and then select appropriate features (such as bag-of-words models, word feature vectors, sentence feature vectors, etc.), and use these features to train a relationship classifier (such as support vector machines, random forests, convolutional neural networks, recurrent neural networks, etc.). After training, the model can predict entity relationship classification for new text to achieve relationship extraction.

[0067] Furthermore, multiple entities and their corresponding attributes, as well as the relationships between entities constitute structured information.

[0068] See also Figure 3 In a specific embodiment, step S1022 includes steps S301 to S305, and each step is described in detail below.

[0069] Step S301, determining entities belonging to a parallel relationship according to the similarity between the entities, and identifying entities belonging to a hierarchical relationship according to the process processing data.

[0070] In this embodiment, a parallel relationship refers to multiple entities having similar properties or status in a certain dimension or attribute, and they are parallel and independent of each other. For example, in the hydrometallurgical zinc smelting process, different raw material chemicals (such as zinc sulfate and copper sulfate) may be regarded as entities in a parallel relationship because they are all raw materials for the reaction but are not dependent on or included in each other.

[0071] The hyponymy relationship refers to a hierarchical or inclusion relationship between entities, where one entity is a category or subset of another entity. For example, in the knowledge graph of hydrometallurgical zinc smelting, "precipitate" may be a hypernym entity, while "zinc hydroxide", "zinc sulfide", etc. are its hyponym entities because they are specific types of precipitates.

[0072] For the coordinate relationship, it is usually necessary to calculate the similarity between entities; for the hyponymy relationship, it is necessary to analyze the hierarchical structure between entities. At the same time, these relationships can also be identified based on the context information in the process data.

[0073] Step S302, generate a structured ontology according to the entities belonging to the coordinate relationship and the entities belonging to the hyponymy relationship.

[0074] In this embodiment, after determining the entities and their relationships, it is necessary to construct a structured ontology. An ontology is a clear description of entities, concepts and their mutual relationships in a certain domain. In the construction of the knowledge graph of hydrometallurgical zinc smelting, the structured ontology serves as the basic framework for knowledge representation, and is used to organize and store various information about the hydrometallurgical zinc smelting process.

[0075] Step S303, extract triples from the fused structured information.

[0076] In this embodiment, a triple consists of a subject, a predicate, and an object. This structure is concise and clear, and can efficiently represent the relationships between entities. In the knowledge graph of hydrometallurgical zinc smelting, triples can be used to describe the relationships between raw materials and products, the associations between process steps, etc.

[0077] The process of extracting triples involves technologies such as natural language processing, information extraction, and semantic analysis to ensure the accurate extraction of useful information from complex texts or data.

[0078] Exemplarily, the representation of triples can be: <zinc calcine, main component, zinc oxide>, <ZnO, generate, zinc sulfate>, <antimony salt, participate in, purification>, <purification, belong to, hydrometallurgical zinc>, <ferrous sulfate, react with, MnO2>.

[0079] Step S304, based on the ontology definition and the triple definition, fuse the structured ontology and the triples to obtain new triples.

[0080] In this embodiment, the structured ontology and the extracted triples are fused, that is, the entities and relationships in the triples are matched and associated with the definitions in the structured ontology to ensure the consistency and accuracy of the knowledge graph.

[0081] The fusion process involves entity alignment, relationship mapping, etc. Entity alignment is used to ensure that entities from different sources are correctly identified as the same entity, and relationship mapping involves matching the extracted relationships with the relationships defined in the ontology.

[0082] It should be noted that during the representation of entities, there may be multiple references pointing to the same entity object, or there may be ambiguity problems with entities having the same name. Through entity disambiguation and coreference resolution, these reference terms can be associated with the correct entity object according to the context of hydrometallurgical zinc smelting. For example, the chemical formula and Chinese description of a certain substance both represent the entity. There is no concept of upper and lower levels within the knowledge graph. Taking the "ZnO" entity and the "hydrometallurgical zinc smelting" entity as an example, it cannot know that "ZnO" and "hydrometallurgical zinc smelting" do not belong to the same type and cannot be compared. Therefore, it is necessary to utilize the determination of the upper and lower relationships of entities in the structured ontology, such as <ZnO, belongs to, leaching>. At this time, the knowledge graph may understand that "ZnO" is a sub-entity under the entity of the leaching process. It is not of the same category as "hydrometallurgical zinc smelting".

[0083] After fusion and processing, the fact expression is transformed into restructured, optimized, and more accurate structured knowledge for storage. Examples of new triples: <90 degrees of high temperature, promotes cobalt removal, Co>, <pH 5.2 - pH 5.4, promotes arsenic removal, AsH3>, <10 g / L - 20 g / L of acid, promotes oxidation, Fe2(SO4)3>, <H3SbO3, belongs to, leaching>.

[0084] Step S305, construct the hydrometallurgical zinc smelting knowledge graph according to the new triples.

[0085] In this embodiment, the hydrometallurgical zinc smelting knowledge graph is constructed according to the new triples after fusion. In this process, a graph database or other suitable graph data structure is used to store and represent the entities, attributes, and relationships in the knowledge graph. In this way, through the combined use of ontology definition and triple definition, the information is more easily understood, queried, and utilized, improving the utilization efficiency of the information.

[0086] In a specific embodiment, the method further includes: obtaining new process treatment data at a preset interval time, and adjusting the hydrometallurgical zinc smelting knowledge graph according to the new process treatment data.

[0087] In this embodiment, in the constructed knowledge graph of hydrometallurgy, the freshness of knowledge is an important indicator for measuring the reliability of the knowledge graph. The data update methods can be divided into two types based on different applicable scenarios, full update and incremental update. Full update is a strategy for updating the entire knowledge graph. It is often executed periodically according to a preset interval. The amount of knowledge is large. For a full update, the previous construction process needs to be executed again. It is necessary to pay attention to and complete the workflow of the entire graph library construction, including data acquisition, cleaning, mining and importing. Incremental update is a small-scale update of part of the data based on the existing data. When the scale of the knowledge graph is large and the scale of knowledge update is small, incremental update is more appropriate.

[0088] For example, in order to adapt to the update of the hydrometallurgical zinc production process, it is necessary to regularly collect the latest process data at preset intervals to retrain and adjust the knowledge graph. The latest production data can be collected at regular intervals (such as 3 months), and then the knowledge graph can be fine-tuned using this data to ensure its accuracy and practicality.

[0089] In a specific embodiment, extracting control rules from the hydrometallurgical zinc smelting knowledge graph according to preset control targets includes: extracting key data corresponding to the preset control targets from the hydrometallurgical zinc smelting knowledge graph; analyzing the key data to obtain the control rules.

[0090] In this embodiment, first, it is necessary to clarify the control targets required in the hydrometallurgical zinc smelting process. These preset control targets may be to increase the recovery rate of zinc, reduce energy consumption, reduce pollutant emissions, optimize process parameters, etc. The determination of the preset control targets is usually based on production needs, environmental protection requirements or economic benefits.

[0091] Next, we need to search in the knowledge graph of hydrometallurgy to find key data related to these goals. As a structured database, the knowledge graph contains various entities, attributes and the relationships between them in the process of hydrometallurgy. Through query statements or graphical interfaces, we can easily retrieve data related to the goals.

[0092] In the search results, it is necessary to screen out key data that are directly related to the preset control targets. These data may include process parameters (such as temperature, pressure, solution concentration, etc.), raw material characteristics (such as zinc ore grade, impurity content, etc.), equipment status (such as reactor efficiency, electrolytic cell current density, etc.) and historical production data. These data are crucial for understanding the current production status, identifying the root causes of problems, and formulating control strategies.

[0093] After extracting the key data, the next step is to analyze the data. There are many methods for data analysis, including but not limited to statistical analysis, trend analysis, correlation analysis, machine learning, etc. Through analysis, the laws and patterns behind the data can be revealed, such as the relationship between process parameters and product quality, the impact of raw material characteristics on production efficiency, etc. These laws and patterns provide a scientific basis for formulating control rules.

[0094] Based on the results of data analysis, control rules can be formulated for preset control targets. Control rules are usually a series of specific operating guidelines or parameter setting suggestions to guide control behaviors in the production process.

[0095] For example, in the process of hydrometallurgy, it is necessary to ensure that the zinc sulfate solution meets the pre-production requirements of electrolysis and remove impurities as much as possible. Therefore, removing the Fe element in the zinc sulfate solution (leaching process) is set as a preset control target. The entities related to the preset control target in the knowledge graph of hydrometallurgy include: Fe3+; Fe(OH); pH; Fe 2 +; MnO2 (oxidant); zinc roasted sand (zinc ore with ZnO as the main component and impurities); NaOH; The relationships related to the preset control target include: Fe3+—Fe(OH)3 generated around pH 5.2; pH—affects precipitation—Fe(OH)3; zinc roasted sand—adjustment—pH; Fe 2 +—MnO2 is oxidized to produce Fe3+; NaOH—adjusts the pH.

[0096] Therefore, based on the production data and process requirements of hydrometallurgical zinc smelting, the following control rules can be defined:

[0097] pH Control:

[0098] 1. When pH < 3, Fe3+ mainly exists in ionic form and does not precipitate.

[0099] 2. When 3≤pH≤5, Fe3+ begins to form Fe(OH) precipitate.

[0100] 3. When pH>5, Fe(OH) precipitation increased significantly.

[0101] Acid concentration: 10g / L ~ 20g / L, the oxidation effect is best; pH <1.9 solution Fe 2+ Almost no oxidation.

[0102] The amount of oxidant: generally 3-5 g / L, Fe 2+ It is basically fully oxidized to Fe3+.

[0103] Amount of NaOH added: According to the current pH value, dynamically adjust the amount of NaOH added to maintain the pH value at around 5.2 (the pH at the end of the leaching process is best controlled at around 5.2).

[0104] In a specific embodiment, adjusting the hydrometallurgical zinc smelting production process according to the control rules includes: predicting the production control results corresponding to the control rules to obtain prediction results, wherein the prediction results include zinc smelting parameters; if the prediction results meet the preset control targets, adjusting the hydrometallurgical zinc smelting production process according to the control rules.

[0105] In this embodiment, the formulated control rules are combined with the prediction model. The prediction model is built based on historical data, process knowledge and machine learning algorithms, and can simulate various variables and their interactions in the hydrometallurgical zinc production process. By incorporating the control rules as input conditions or constraints into the prediction model, the possible production results after implementing these rules can be simulated.

[0106] The prediction model combined with the control rules is used to predict the results of hydrometallurgical zinc production control. The prediction results include zinc recovery rate, cost and other zinc smelting parameters, as well as energy consumption, pollutant emissions, product quality indicators and other aspects. These prediction results reflect the state and performance that the production process may achieve under specific control rules.

[0107] Analyze and evaluate the forecast results to determine whether they meet the preset control objectives. This includes comparing the gap between the forecast results and the preset control objectives, evaluating the potential impact of the control rules on production efficiency and product quality, and identifying possible risks and challenges. Through analysis and evaluation, the effectiveness and feasibility of the control rules can be judged.

[0108] Adjustments are made to the hydrometallurgical zinc production process based on the analysis and evaluation of the forecast results. If the forecast results show that the control rules can significantly improve production efficiency and product quality, and the risks are controllable, then it can be decided to implement these control rules. Adjustments may involve changing process parameters, optimizing raw material ratios, adjusting equipment operating conditions, etc. During the implementation process, it is necessary to pay close attention to changes in production data to ensure the effectiveness and stability of the adjustment measures.

[0109] Compare the preset control target with the predicted result to form a feedback mechanism. If there is a large deviation between the actual result and the predicted result, it is necessary to analyze the cause and take corresponding optimization measures. This may include adjusting the prediction model, revising the control rules, or improving the production process control. Through continuous feedback and optimization, the accuracy of the prediction and the stability of the production process can be gradually improved.

[0110] The hydrometallurgical zinc smelting control method based on the knowledge graph proposed in this embodiment collects the process processing data of the slime ion unit of hydrometallurgical zinc smelting; based on the process knowledge and ion reaction mechanism of hydrometallurgical zinc smelting, constructs the hydrometallurgical zinc smelting knowledge graph according to the process processing data; extracts the control rules from the hydrometallurgical zinc smelting knowledge graph according to the preset control target, and adjusts the hydrometallurgical zinc smelting production process according to the control rules. In this way, the knowledge graph is constructed according to the process processing data of the slime ion unit of hydrometallurgical zinc smelting, and the control rules are extracted based on the knowledge graph to control the hydrometallurgical zinc smelting production process. The intelligent coordinated control of the slime ions produced in the whole process of hydrometallurgical zinc smelting can be realized through the association relationship of the knowledge graph, thereby improving the technical level of zinc smelting production.

[0111] Example 2

[0112] In addition, the present disclosure provides a knowledge graph-based hydrometallurgical zinc smelting control device 400, see Figure 4 , the device comprises:

[0113] The acquisition module 401 is used to acquire the process data of the sludge ion production unit of hydrometallurgy;

[0114] A construction module 402 is used to construct a knowledge graph of hydrometallurgy based on process knowledge and ion reaction mechanism of hydrometallurgy according to the process processing data;

[0115] The control module 403 is used to extract control rules from the hydrometallurgical zinc smelting knowledge graph and adjust the hydrometallurgical zinc smelting production process according to the control rules.

[0116] Optionally, the construction module 402 is also used to extract knowledge from the process processing data based on the process knowledge and the ion reaction mechanism to obtain structured information; perform knowledge fusion on the structured information, and perform knowledge processing on the fused structured information based on the ontology definition and the triple definition to obtain the hydrometallurgical zinc smelting knowledge graph.

[0117] Optionally, construction module 402 is also used to extract ion reaction information and process information from the process processing data based on the process knowledge and the ion reaction mechanism, and extract multiple entities and their corresponding attributes, as well as the relationship between the entities based on the ion reaction information and the process information; determine the structured information based on the multiple entities and their corresponding attributes, as well as the relationship between the entities.

[0118] Optionally, construction module 402 is further used to determine entities belonging to a parallel relationship based on the similarity between each of the entities, and identify entities belonging to a hierarchical relationship based on the process processing data; generate a structured ontology based on the entities belonging to the parallel relationship and the entities belonging to the hierarchical relationship; extract triples from the fused structured information; based on the ontology definition and the triple definition, fuse the structured ontology and the triple to obtain a new triple; and construct the hydrometallurgical zinc smelting knowledge graph based on the new triples.

[0119] Optionally, the construction module 402 is further used to obtain new process processing data according to a preset interval time, and adjust the hydrometallurgical zinc smelting knowledge graph according to the new process processing data.

[0120] Optionally, the control module 403 is further used to extract key data corresponding to the preset control target from the hydrometallurgical zinc smelting knowledge graph; analyze the key data to obtain the control rules.

[0121] Optionally, the control module 403 is also used to predict the production control results corresponding to the control rules to obtain prediction results, and the prediction results include zinc smelting parameters; if the prediction results meet the preset control targets, the wet zinc smelting production process is adjusted according to the control rules.

[0122] The device provided in the embodiment of the present disclosure can execute the steps of the knowledge graph-based hydrometallurgical zinc smelting control method provided in Example 1, which will not be described again to avoid repetition.

[0123] The hydrometallurgical zinc smelting control device based on the knowledge graph proposed in this embodiment collects the process processing data of the slime ion unit of hydrometallurgical zinc smelting; based on the process knowledge and ion reaction mechanism of hydrometallurgical zinc smelting, constructs the hydrometallurgical zinc smelting knowledge graph according to the process processing data; extracts the control rules from the hydrometallurgical zinc smelting knowledge graph according to the preset control target, and adjusts the hydrometallurgical zinc smelting production process according to the control rules. In this way, the knowledge graph is constructed according to the process processing data of the slime ion unit of hydrometallurgical zinc smelting, and the control rules are extracted based on the knowledge graph to control the hydrometallurgical zinc smelting production process, and the intelligent coordinated control of the slime ions produced in the whole process of hydrometallurgical zinc smelting can be realized through the association relationship of the knowledge graph, thereby improving the technical level of zinc smelting production.

[0124] Example 3

[0125] In addition, an embodiment of the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the knowledge graph-based hydrometallurgical zinc smelting control method described in Example 1 is implemented.

[0126] The device provided in the embodiment of the present disclosure can execute the steps of the knowledge graph-based hydrometallurgical zinc smelting control method provided in Example 1, which will not be described again to avoid repetition.

[0127] Example 4

[0128] The disclosed embodiment proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the knowledge graph-based hydrometallurgical zinc smelting control method described in Embodiment 1.

[0129] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0130] The computer-readable storage medium provided in this embodiment can implement the knowledge graph-based hydrometallurgical zinc smelting control method provided in Example 1. To avoid repetition, it will not be described here.

[0131] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0132] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0133] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A method for controlling hydrometallurgy of zinc based on knowledge graph, characterized in that: include: Collect process data of the sludge ion production unit of hydrometallurgical zinc smelting; Based on the process knowledge and ion reaction mechanism of hydrometallurgy, a knowledge graph of hydrometallurgy is constructed according to the process processing data; According to preset control objectives, control rules are extracted from the hydrometallurgical zinc smelting knowledge graph, and the hydrometallurgical zinc smelting production process is adjusted according to the control rules.

2. The knowledge graph-based hydrometallurgical zinc smelting control method according to claim 1, characterized in that: The process knowledge and ion reaction mechanism based on hydrometallurgy zinc smelting are used to construct a knowledge graph of hydrometallurgy zinc smelting according to the process processing data, including: Extracting knowledge from the process data based on the process knowledge and the ion reaction mechanism to obtain structured information; The structured information is fused with knowledge, and the fused structured information is processed with knowledge based on the ontology definition and the triple definition to obtain the hydrometallurgical zinc smelting knowledge graph.

3. The knowledge graph-based hydrometallurgical zinc smelting control method according to claim 2, characterized in that: The step of extracting knowledge from the process data based on the process knowledge and the ion reaction mechanism to obtain structured information includes: Based on the process knowledge and the ion reaction mechanism, ion reaction information and process information are extracted from the process processing data, and multiple entities and their corresponding attributes, as well as the relationship between the entities are extracted according to the ion reaction information and the process information; The structured information is determined according to the multiple entities and their corresponding attributes, and the relationship between the entities.

4. The knowledge graph-based hydrometallurgical zinc smelting control method according to claim 3, characterized in that: The knowledge processing of the fused structured information based on the ontology definition and the triple definition to obtain the knowledge graph of hydrometallurgy zinc smelting includes: Determining entities in a parallel relationship based on the similarities between the entities, and identifying entities in a hierarchical relationship based on the process data; Generate a structured ontology according to the entities belonging to the parallel relationship and the entities belonging to the hierarchical relationship; Extracting triples from the fused structured information; Based on the ontology definition and the triple definition, the structured ontology and the triple are merged to obtain a new triple; The knowledge graph of hydrometallurgy is constructed according to the new triples.

5. The method for controlling zinc hydrometallurgy based on knowledge graph according to claim 1, characterized in that: The method further comprises: New process data is acquired according to a preset time interval, and the knowledge graph of hydrometallurgy is adjusted according to the new process data.

6. The method for controlling zinc hydrometallurgy based on knowledge graph according to claim 1, characterized in that: The extracting of control rules from the hydrometallurgical zinc smelting knowledge graph according to the preset control target includes: Extracting key data corresponding to the preset control target from the hydrometallurgical zinc smelting knowledge graph; The key data are analyzed to obtain the control rules.

7. The knowledge graph-based hydrometallurgical zinc smelting control method according to claim 1, characterized in that: The step of adjusting the hydrometallurgical zinc production process according to the regulation rules comprises: Predicting the production control result corresponding to the control rule to obtain a prediction result, wherein the prediction result includes zinc smelting parameters; If the prediction result meets the preset control target, the hydrometallurgical zinc smelting production process is adjusted according to the control rules.

8. A knowledge graph-based hydrometallurgical zinc smelting control device, characterized in that: include: The acquisition module is used to collect the process data of the sludge ion production unit of hydrometallurgy; A construction module for constructing a knowledge graph of hydrometallurgy based on process knowledge and ion reaction mechanism of hydrometallurgy according to the process processing data; A control module is used to extract control rules from the hydrometallurgical zinc smelting knowledge graph and adjust the hydrometallurgical zinc smelting production process according to the control rules.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the knowledge graph-based hydrometallurgical zinc smelting control method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the knowledge graph-based hydrometallurgical zinc smelting control method as described in any one of claims 1 to 7.

Images