A method for monitoring abnormalities in electrolytic production

Abstract

The embodiment of the present specification provides an abnormality monitoring method for electrolytic production, comprising: acquiring production monitoring information; determining production abnormality information based on the production monitoring information; determining process improvement information or an abnormality processing scheme based on the production abnormality information.

Description

[0001] Case Analysis

[0002] This application is a divisional application of Chinese application filed on March 28, 2022, with application number 202210308708.8 and entitled "An Improved Method and System for Electrolysis Production". Technical Field

[0003] This manual relates to the field of electrolytic production, and in particular to a method for monitoring anomalies in electrolytic production. Background Technology

[0004] In electrolysis production, abnormal situations sometimes occur in various processes (such as mold deformation). These abnormalities are usually significant factors affecting the pass rate and production efficiency of electrolysis production. Monitoring and adjusting the electrolysis production line is crucial for ensuring its normal operation.

[0005] Therefore, it is desirable to provide an anomaly monitoring method for electrolysis production to improve electrolysis production efficiency. Summary of the Invention

[0006] One embodiment of this specification provides an anomaly monitoring method for electrolytic production. The method includes: acquiring production monitoring information; the production monitoring information includes at least one of anode plate casting information and shaping information; determining production anomaly information based on the production monitoring information; and determining process improvement information or anomaly handling plan based on the production anomaly information.

[0007] One embodiment of this specification provides an abnormal monitoring system for electrolytic production, comprising: an acquisition module for acquiring production monitoring information; the production monitoring information including at least one of anode plate casting information and shaping information; a first determination module for determining production abnormal information based on the production monitoring information; and a second determination module for determining process improvement information or abnormal handling plan based on the production abnormal information.

[0008] One embodiment of this specification provides an anomaly monitoring device for electrolytic production. The device includes: at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least a portion of the computer instructions to implement a method for anomaly monitoring in electrolytic production.

[0009] One embodiment of this specification provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes an abnormal monitoring method for electrolysis production. Attached Figure Description

[0010] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0011] Figure 1 These are schematic diagrams illustrating application scenarios of the improved electrolysis production system according to some embodiments of this specification;

[0012] Figure 2 This is a schematic diagram of the modules of an improved electrolysis production system according to some embodiments of this specification;

[0013] Figure 3 This is an exemplary flowchart of an improved electrolytic production method according to some embodiments of this specification;

[0014] Figure 4 This is a schematic diagram illustrating data acquisition of an improved electrolysis production system according to some embodiments of this specification;

[0015] Figure 5 This is an exemplary flowchart illustrating the analysis of electrolysis production monitoring information to determine electrolysis production improvement information according to some embodiments of this specification;

[0016] Figure 6 This is an exemplary flowchart illustrating the improvement of electrolysis production processes based on electrolysis production improvement information, according to some embodiments of this specification.

[0017] Figure 7 This is a schematic diagram illustrating the determination of electrolytic production parameter adjustment information based on the difference vector using an adjustment amount confirmation model according to some embodiments of this specification;

[0018] Figure 8 This is a schematic diagram illustrating the determination of adjustment information for electrolytic production parameters based on a difference vector using a first adjustment amount confirmation model and / or a second adjustment amount confirmation model, according to some embodiments of this specification.

[0019] Figure 9 This is a schematic diagram illustrating the determination of adjustment information for electrolytic production parameters based on a difference vector using an adjustment amount confirmation model, according to other embodiments of this specification.

[0020] Figure 10 This is an exemplary flowchart illustrating how an anomaly determination model, as shown in some embodiments of this specification, determines adjustment information for electrolysis production parameters. Detailed Implementation

[0021] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0022] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0023] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0024] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0025] Figure 1 This is a schematic diagram illustrating an application scenario of an improved electrolysis production system according to some embodiments of this specification.

[0026] In some embodiments, application scenario 100 may include a server 110, a network 120, one or more terminal devices 130, a storage device 140, a data acquisition device 150, and an electrolysis production line 160. Application scenario 100 can monitor various process steps in electrolysis production (e.g., casting, shaping, electrolysis, etc.) by implementing the methods and / or processes disclosed in this specification, and inspect the anode plates and / or cathode plates to obtain production monitoring information (e.g., anode plate casting information, shaping process parameter information, etc.). Based on the production monitoring information, it can determine electrolysis production improvement information (e.g., prediction information for non-conforming products, non-conforming product disposal information, etc.), and then feed it back to the production process for corresponding adjustments and improvements, thereby improving the efficiency and quality of electrolysis production.

[0027] Server 110 can be located in places including, but not limited to, the control room of an electrolysis production line, an electrolysis production management center, etc. In some embodiments, server 110 is equipped with a collaborative platform for directing and coordinating the various tasks of electrolysis production personnel. These personnel may include electrolysis production operators, production safety managers, electrolysis production comprehensive managers, electrolysis technology experts, and other personnel involved in electrolysis production operation and management. For example, server 110 can acquire information such as electrode plate information, electrolysis production process monitoring information, electrolysis production process anomaly information, and electrolysis production monitoring workflow.

[0028] Server 110 can communicate with terminal device 130, storage device 140, data acquisition device 150, and / or electrolysis production line 160 to provide various functions of application scenario 100. In some embodiments, server 110 can receive, for example, relevant detection information (e.g., electrode composition information, casting process parameter information, etc.) from terminal device 130 after data acquisition device 150 has detected electrolysis production line 160 via network 120. In other embodiments, server 110 can receive relevant electrolysis production process information (e.g., temperature information of casting furnace, electrode tapping time, etc.) in electrolysis production line 160 via network 120.

[0029] In some embodiments, server 110 may be a single server or a group of servers. In some embodiments, server 110 may be locally connected to network 120 or remotely connected to network 120. In some embodiments, server 110 may be implemented on a cloud platform.

[0030] Network 120 can facilitate the exchange of information and / or data. In some embodiments, one or more components of application scenario 100 (e.g., server 110, network 120, etc.) can send information and / or data to another component in application scenario 100 via network 120.

[0031] In some embodiments, the user (e.g., electrolysis production worker, technical expert, etc.) may be the owner of the terminal device 130. The terminal device 130 may receive user requests and send information related to the requests to the server 110 via the network 120. For example, the terminal device 130 may receive a user requesting the transmission of electrode plate detection information or production process parameter information, and send the relevant information to the server 110 via the network 120. The terminal device 130 may also receive information from the server 110 via the network 120. For example, the terminal device 130 may receive production monitoring information related to the data acquisition device 150 or the electrolysis production line 160 from the server 110. One or more pieces of production monitoring information may be displayed on the terminal device 130. As another example, the server 110 may send production improvement information (e.g., mold replacement, electrolyte adjustment, etc.) or production anomaly information (e.g., excessive electrolyte impurity content, mold anomaly, etc.) generated based on the detection information to the terminal device 130.

[0032] In some embodiments, terminal device 130 may include mobile devices, tablet computers, laptop computers, vehicle-mounted devices, or any combination thereof. In some embodiments, terminal device 130 may include a signal transmitter and a signal receiver, configured to communicate with data acquisition device 150 to obtain detection information of the sample to be tested. In some embodiments, terminal device 130 may be fixed and / or mobile. For example, terminal device 130 may be directly installed on server 110 and / or electrolysis production equipment, becoming part of server 110 and / or electrolysis production equipment. As another example, terminal device 130 may be a mobile device, which electrolysis production workers can carry to a location relatively far from server 110, data acquisition device 150, and electrolysis production line 160. Terminal device 130 can connect to and / or communicate with server 110, data acquisition device 150, and / or electrolysis production line 160 via network 120.

[0033] In some embodiments, storage device 140 may be connected to network 120 to communicate with one or more components of application scenario 100 (e.g., server 110, terminal device 130, data acquisition device 150). In some embodiments, storage device 140 may be part of server 110.

[0034] Storage device 140 may store data and / or instructions. Data may include information relating to a user, terminal device 130, data acquisition device 150, etc. In some embodiments, storage device 140 may store data acquired from terminal device 130, data acquisition device 150, and / or electrolysis production line 160. In some embodiments, storage device 140 may store data and / or instructions used by server 110 to perform or use in order to complete the exemplary methods described herein.

[0035] In some embodiments, storage device 140 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), or any combination thereof. In some embodiments, storage device 140 may be implemented on a cloud platform.

[0036] Data acquisition device 150 can acquire production monitoring information from the electrolysis production line. More details regarding the detection information can be found in [link to relevant documentation]. Figure 4 The details and related descriptions will not be repeated here.

[0037] In some embodiments, the data acquisition device 150 can be implemented by various detection devices or methods, such as including a manual detection module 150-1, a barcode scanning detection module 150-2, an infrared detection module 150-3, an image acquisition module 150-4, a temperature detection module 150-5, an ultrasonic detection module 150-6, a sampling detection module 150-7, and a timing module 150-8. Further descriptions of the manual detection module 150-1, barcode scanning detection module 150-2, infrared detection module 150-3, image acquisition module 150-4, temperature detection module 150-5, ultrasonic detection module 150-6, sampling detection module 150-7, and timing module 150-8 can be found in [reference needed]. Figure 4 The details and related descriptions will not be repeated here.

[0038] An electrolysis production line 160 refers to a system or apparatus used to realize the electrolysis production process. The electrolysis production line 160 may include process steps such as casting process 160-1, shaping process 160-2, plate arrangement process, tank loading process, electrolysis process 160-3, and tank unloading process. In some embodiments, the electrolysis production line 160 may include electrolysis production equipment (e.g., casting furnace, shaping milling machine, electrolytic cell, etc.), inspection equipment (e.g., inspection instrument, inspection device, inspection vehicle, inspection robot), positioning device, etc.

[0039] In some embodiments, the electrolytic production equipment (e.g., casting furnace, milling machine, electrolytic cell, etc.) in the electrolytic production line 160 can be connected to the network 120 to communicate with one or more components of the application scenario 100 (e.g., server 110, terminal device 130, data acquisition device 150). For example, the electrolytic production line 160 can transmit production monitoring information (e.g., plate detection information, capacity information, etc.) to the server 110 via the network 120.

[0040] In some embodiments, server 110 can determine electrolysis production improvement information (e.g., electrolyte adjustment information, additive adjustment information, electrode adjustment information, casting production parameter adjustment information, casting mold deformation information, etc.) and / or electrolysis production anomaly information (e.g., electrode appearance anomaly, casting furnace temperature anomaly, etc.) based on production monitoring information (e.g., electrode plate detection information, capacity information, etc.) and transmit it to electrolysis production line 160 via network 120. In some embodiments, electrolysis production line 160 can provide feedback improvements to corresponding parameters or process steps in electrolysis production based on the electrolysis production improvement information. In some embodiments, electrolysis production line 160 can provide prompts to electrolysis production personnel based on electrolysis production anomaly information or anomaly handling solutions.

[0041] It should be noted that application scenario 100 is provided for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can make various modifications or variations based on the description in this specification. For example, application scenario 100 may also include a database. However, these changes and modifications will not depart from the scope of this specification.

[0042] Figure 2 This is a schematic diagram of the modules of an improved electrolysis production system 200 according to some embodiments of this specification.

[0043] In some embodiments, such as Figure 2 As shown, the electrolysis production improvement system 200 may include an acquisition module 210, a determination module 220, and an improvement module 230. In some embodiments, the electrolysis production improvement system 200 may be subdivided into multiple specific subsystems based on different functions. For example, the electrolysis production improvement system 200 may include an electrolysis production parameter determination system, an electrolysis production anomaly monitoring system, etc.

[0044] The acquisition module 210 can be used to acquire production monitoring information.

[0045] In some embodiments, the production monitoring information includes at least one of: anode plate casting information and shaping information. Further, the anode plate casting information includes at least one of: casting process information and casting inspection information; the shaping information includes at least one of: shaping process information and shaping inspection information.

[0046] In some embodiments, the acquisition module 210 can be used to acquire the quality characteristics of the anode plate based on electrolytic production monitoring information; the quality characteristics include at least the composition information of the anode plate. In some embodiments, the anode plate is provided with a readable information carrier, and the acquisition module 210 can be used to acquire the electrolytic production monitoring information of the anode plate based on scanning the readable information carrier. For more details on determining how to acquire production monitoring information, please refer to [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0047] The determination module 220 can be used to determine electrolysis production improvement information based on production monitoring information.

[0048] In some embodiments, electrolysis production improvement information includes at least one of the following: improvement information on process parameters in the electrolysis production process, prediction information on nonconforming products, traceability information on production anomalies, and disposal information on nonconforming products.

[0049] In some embodiments, the determining module 220 can be used to determine electrolytic production parameters based on the difference between the quality characteristics and standard characteristics of the anode plate; the standard characteristics include at least the composition information of the standard anode plate; the electrolytic production parameters include at least one of electrolyte ratio parameters and additive ratio parameters. In some embodiments, the determining module 220 can be used to determine adjustment information for the electrolytic production parameters based on the difference between the quality characteristics and standard characteristics of the anode plate. Further, the determining module 220 can determine the difference vector between the quality characteristics and the standard characteristics; based on the difference vector, the adjustment information for the electrolytic production parameters is determined through an adjustment amount confirmation model; the adjustment information includes electrolyte ratio adjustment amount and / or additive ratio adjustment amount.

[0050] In some embodiments, the determining module 220 can be used to determine production anomaly information based on production monitoring information. Further, the determining module 220 can be used to determine the characteristic information of the anode plate to be evaluated based on production monitoring information, the characteristic information including at least one of composition characteristics, weight characteristics, and casting mold; and predict whether the anode plate to be evaluated is a qualified product based on the characteristic information of the anode plate to be evaluated. Further, the determining module 220 can obtain the similarity between the characteristic information of the current anode plate and the historical characteristic information of multiple historically produced unqualified anode plates; use the similarity as the risk level of the unqualified product; and predict whether the anode plate to be evaluated is a qualified product based on the risk level.

[0051] In some embodiments, the determining module 220 can be used to determine process improvement information or anomaly handling solutions based on production anomaly information. Further, the determining module 220 can be used to determine abnormal parameters of the anode plate based on production monitoring information; and based on the processing of abnormal parameters of the anode plate using an anomaly determination model, determine the anomaly type, which includes at least one of mold anomaly, casting parameter anomaly, and ore source anomaly. For further explanation on determining electrolysis production improvement information, please refer to [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0052] In some embodiments, the determining module 220 may include a first determining module (not shown in the figure), which may acquire the quality characteristics of the anode plate based on electrolysis production monitoring information; the quality characteristics include at least the composition information of the anode plate, and the electrolysis production parameters are determined based on the difference between the quality characteristics of the anode plate and the standard characteristics; wherein, the standard characteristics include at least the composition information of the standard anode plate; the electrolysis production parameters include at least one of electrolyte ratio parameters and additive ratio parameters.

[0053] In some embodiments, the determining module 220 may include a second determining module (not shown in the figure), which may determine production anomaly information based on production monitoring information and determine process improvement information or anomaly handling plan based on the production anomaly information.

[0054] The improvement module 230 can be used to improve the electrolysis production process based on electrolysis production improvement information.

[0055] In some embodiments, the improvement module 230 can optimize the process based on received electrolysis production improvement information. In some embodiments, the improvement module 230 can take timely emergency measures based on received abnormal situations in electrolysis production. For more information on improving electrolysis production processes, please refer to [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0056] In some embodiments, the electrolysis production improvement system 200 may further include a transmission module (not shown in the figure), which can be used to transmit abnormal situations and / or electrolysis production improvement information to the management control center or the corresponding process. The transmission method can be wired, such as through open wires, cables, and optical fibers, or wireless, such as through microwave, satellite, scattering, ultra-shortwave, shortwave, Wi-Fi, Bluetooth, and infrared.

[0057] It should be noted that the above description of the electrolysis production improvement system 200 and its modules is for ease of description only and should not limit this specification to the scope of the illustrated embodiments. It is understood that those skilled in the art, after understanding the principle of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from this principle. In some embodiments, Figure 1 The acquisition module 210, determination module 220, and improvement module 230 disclosed herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. For example, the modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0058] Figure 3 This is an exemplary flow chart of an improved electrolytic production method according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, process 300 may be performed by electrolysis production improvement system 200.

[0059] Step 310: Obtain production monitoring information. In some embodiments, step 310 may be performed by the acquisition module 210.

[0060] Production monitoring information can be information related to anode plate production. It is understood that anode plate production may include multiple processes (e.g., casting, shaping, etc.), and production monitoring information may include information related to at least one process in anode plate production.

[0061] In some embodiments, production monitoring information may include at least one of anode plate casting information and shaping information.

[0062] The casting information can be information related to the casting of the anode plate. Understandably, the anode plate casting process may include heating and melting the raw materials used to form the anode plate into a liquid state, then pouring the liquid raw material into an anode plate mold and allowing it to cool and solidify. For example, the casting information may include relevant information before casting (e.g., raw material composition), relevant information during casting (e.g., furnace operating temperature, mold type, casting time), and relevant information after casting (e.g., anode plate dimensions).

[0063] In some embodiments, the casting information of the anode plate may include at least one of casting process information and casting inspection information. The casting process information may be information related to the process during casting. The casting process information may include at least one of the following: furnace information (e.g., furnace temperature, capacity, etc.), casting formula (e.g., the composition ratio of the ore source used for casting), casting mold information (e.g., casting mold number, size, service life, maintenance time, etc.), furnace exit time (e.g., casting time and furnace exit time), and furnace exit weight (e.g., the weight information of the cast anode plate and the weight of the remaining residue).

[0064] The casting inspection information can be information obtained by inspecting the anode plates during the casting process. The casting inspection information can include at least one of the following: composition information (e.g., mineral source composition and anode plate composition) and anode plate appearance information (e.g., thickness information, size information, flatness, verticality information).

[0065] The shaping information can be related to the shaping of the anode plate. Understandably, the anode plate shaping process can include shaping the cooled and formed anode plate to make it flatter and prevent subsequent deformation of the anode plate from easily contacting the cathode plate, causing a short circuit and reducing production efficiency. The shaping information can include relevant information before shaping (e.g., the weight and dimensions of the anode plate before shaping), relevant information during shaping (e.g., parameters of the shaping equipment (e.g., clamps, milling cutters, etc.), shaping time, etc.), and relevant information after shaping (e.g., the weight and dimensions of the anode plate after shaping).

[0066] In some embodiments, the shaping information may include at least one of shaping process information and shaping inspection information. The shaping process information may be information related to the shaping process. For example, the shaping process information may include at least one of the following: the model and conveying speed of the conveyor belt used to transport the anode plate to be shaped; the model and working parameters of the pressure ear (e.g., the pressure generated by the pressure ear); and the model and working parameters of the grinding tool (e.g., the milling cutter) (e.g., the milling cutter speed). The shaping inspection information may be information obtained by inspecting the anode plate during or after shaping. The shaping inspection information may include at least one of the following: weight information, thickness information, size information, flatness, and perpendicularity information of the shaped anode plate. The flatness of the anode plate can characterize the degree of unevenness of the anode plate surface, and the perpendicularity information can characterize the angle between the anode plate and the horizontal plane when the anode plate is placed vertically on the horizontal plane.

[0067] In some embodiments, the acquisition module 210 can acquire production monitoring information through the data acquisition device 150. For further description of the data acquisition device 150, please refer to... Figure 4 The details and related descriptions will not be repeated here.

[0068] Step 320: Determine electrolysis production improvement information based on production monitoring information. In some embodiments, step 320 may be performed by the determination module 220.

[0069] In some embodiments, electrolysis production improvement information may be information related to adjustments to electrolysis-related processes. These electrolysis-related processes may include anode plate production processes (e.g., casting, shaping, etc.) and electrometallurgical processes. For example, electrolysis production improvement information may include information on improvements to the parameters of casting equipment (e.g., improved furnace operating temperature, mold type, casting time, etc.) and information on improvements to the parameters of shaping equipment (e.g., improved parameters of equipment such as pressure plates and milling cutters, etc.).

[0070] In some embodiments, electrolysis production improvement information may include at least one of the following: improvement information on process parameters in the electrolysis production process, prediction information on nonconforming products, traceability information on production anomalies, and disposal information on nonconforming products.

[0071] Information on improvements to process parameters in the electrolytic production process can be information related to adjustments to process parameters for anode plate production and / or electrometallurgy. For example, process parameters for anode plate production can include at least one of the following: casting process parameters (e.g., ore mix ratio, flow rate and temperature of the molten molten metal, equipment parameters, etc.) and shaping equipment operating parameters (e.g., pressure of the pressure lugs, rotational speed of the milling cutter, etc.).

[0072] In some embodiments, the improvement information for process parameters in the electrolysis production process may further include electrolysis production parameters. Electrolysis production parameters can be electrometallurgical process parameters, and may include at least one of electrolyte ratio, additive ratio, etc. Specifically, the electrolyte ratio can be the proportion of various components of the electrolyte (e.g., ethylene carbonate, propylene carbonate, diethyl carbonate, dimethyl carbonate, methyl ethyl carbonate, lithium hexafluorophosphate, phosphorus pentafluoride, hydrofluoric acid, and water, etc.), and the additive ratio can be the proportion of additives added to the electrolyte (e.g., thiourea, bone glue, avitamin, etc.).

[0073] In some embodiments, the improvement information of process parameters in the electrolysis production process may further include process improvement information, which may be information related to adjusting the process parameters of anode plate production. For example, the process improvement information may include at least one of the following: improvement information of casting process parameters (e.g., ore ratio, flow rate and temperature of the casting molten broth, equipment parameters, etc.) and improvement information of shaping equipment operating parameters (e.g., pressure of the pressure lugs, rotation speed of the milling cutter, etc.).

[0074] The information for predicting nonconforming products can be information related to whether the anode plates after casting and / or shaping meet the quality requirements.

[0075] Traceability information for production anomalies can be information related to equipment or process parameters associated with the defective anode plates. For example, traceability information for production anomalies may include the furnace and / or mold number that produced the defective anode plates, and the parameters used in producing the defective anode plates (e.g., the furnace operating temperature, raw material composition, etc.).

[0076] Information on the handling of non-conforming products can be information related to the handling of non-conforming anode plates.

[0077] In some embodiments, the disposal information for nonconforming products may include an exception handling plan, which may be information related to the disposal of nonconforming anode plates. For example, the disposal information for nonconforming products may include complete remelting, complete placement for future use, and partial remelting and partial placement for future use. In some embodiments, for nonconforming products that require partial remelting and partial placement for future use, the proportion of these two disposal methods to the total number of nonconforming products may be further determined. For an explanation of determining the proportion, please refer to [link to relevant documentation]. Figure 5 Partial explanation.

[0078] In some embodiments, the determining module 220 can determine electrolysis production improvement information in various ways. For example, the determining module 220 can determine electrolysis production improvement information based on historical data and production monitoring information. The historical data may include production monitoring information at least one historical time point and its corresponding electrolysis production improvement information. It is understood that the determining module 220 may use electrolysis production improvement information corresponding to a historical time point similar to the current production monitoring information as the current electrolysis production improvement information.

[0079] For example, module 220 can determine electrolysis production improvement information based on production monitoring information using human experience. Alternatively, industry experts can determine electrolysis production improvement information based on production monitoring information.

[0080] In some embodiments, the determining module 220 can analyze electrolysis production improvement information to determine electrolysis production improvement information. For more details on analyzing electrolysis production improvement information and determining electrolysis production improvement information, please refer to [link to relevant documentation]. Figure 5 The details and related descriptions will not be repeated here.

[0081] Step 330: Improve the electrolysis production process based on electrolysis production improvement information. In some embodiments, step 330 may be performed by improvement module 230.

[0082] In some embodiments, the improvement module 230 can apply electrolysis production improvement information to the electrolysis production process. For example, the improvement module 230 can set the electrolyte ratio, additive ratio, etc. of the electrolytic cell according to the electrolysis production improvement information in the electrolysis production improvement information.

[0083] For more details on improving electrolysis production processes based on electrolysis production improvement information, please refer to [link to relevant documentation]. Figure 6 The details and related descriptions will not be repeated here.

[0084] In some embodiments, by acquiring production monitoring information, determining electrolysis production improvement information based on the production monitoring information, and improving the electrolysis production process based on the electrolysis production improvement information, abnormal situations can be detected in a timely manner, and the electrolysis production process can be improved in a timely manner to ensure the normal operation of the electrolysis production process and reduce losses.

[0085] It should be noted that the above description of process 300 is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to process 300 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0086] Figure 4 This is a schematic diagram illustrating data acquisition of an improved electrolytic production system according to some embodiments of this specification.

[0087] The electrolysis production improvement system can acquire production monitoring information 420 of the electrolysis production line 160 (such as casting process 160-1, shaping process 160-2, electrolysis process 160-3, etc.) through the data acquisition device 150.

[0088] The data acquisition device 150 is a unit module for acquiring relevant data (e.g., production monitoring information) for the electrolysis production line 160. The relevant data may be quality characteristic information of the anode plates and / or cathode plates (e.g., appearance, physical, and chemical information). The relevant data may also be electrolysis process parameter information (e.g., casting process parameters, shaping process parameters, and electrolysis process parameters). For more detailed descriptions of the quality characteristic information of the anode plates and the electrolysis process parameter information, please refer to [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0089] In some embodiments, the data acquisition device 150 can acquire production monitoring information based on at least one of the following methods: manual inspection, barcode scanning, infrared detection, image processing, ultrasonic detection, laser detection, sampling, and timing. For example, the data acquisition device 150 may include a manual inspection module 150-1, a barcode scanning inspection module 150-2, an infrared inspection module 150-3, an image acquisition module 150-4, a temperature inspection module 150-5, an ultrasonic detection module 150-6, a sampling inspection module 150-7, and a timing module 150-8.

[0090] In some embodiments, the manual inspection module 150-1 can perform manual inspection, observation, and manual input recording of production monitoring information.

[0091] In some embodiments, electrolysis production workers can manually observe, detect, and input casting information (e.g., casting furnace information, casting ore formula, casting mold information, casting exit time), shaping information (e.g., shaping equipment information), electrolysis information (e.g., cell entry time, electrolytic cell parameters), quality characteristics of anode plates in each process (anode plate composition information, anode plate shape information, anode plate weight), ore source information (e.g., ore source information, ore source retention time), actual production anomaly information of the electrolysis process, output information, etc.

[0092] In some embodiments, the barcode scanning detection module 150-2 can read readable information carriers (e.g., QR codes, barcodes, RFID tags, etc.) set on the equipment and / or anode plates on the electrolysis production line to obtain production monitoring information.

[0093] In some embodiments, the electrolysis production equipment is equipped with a readable information carrier, and the relevant production monitoring information 420 of the electrolysis production equipment can be obtained by scanning the readable information carrier. The barcode scanning detection module 150-2 can perform barcode scanning operations. For example, each casting mold can be equipped with a corresponding information carrier to record mold information, so that the casting mold information (such as mold identification (e.g., number), manufacturer, and service life) can be directly obtained by scanning the code. The code scanning detection module 150-2 can read the QR code set on the casting mold to obtain the casting mold information. Similarly, each shaping device can be equipped with a corresponding information carrier to record shaping device information, so that the shaping device information (such as shaping device model, manufacturer, service life, and maintenance interval) can be directly obtained by scanning the code. The code scanning detection module 150-2 can read the QR code set on the shaping device to obtain the shaping device information. Likewise, each electrolytic cell can be equipped with a corresponding information carrier to record electrolytic cell information, so that the cell information (electrolytic cell identification (e.g., number), manufacturer, service life, and operating precautions) can be directly obtained by scanning the code. The code scanning detection module 150-2 can read the QR code set on the electrolytic cell to obtain the electrolytic cell information.

[0094] In some embodiments, a readable information carrier may be provided on the anode plate, storing the anode plate's identification identifier. Production monitoring information 420 corresponding to the anode plate's identification identifier can be obtained by scanning the readable information carrier. In some embodiments, the barcode scanning module 150-2 can perform a barcode scanning operation.

[0095] In some embodiments, the system can transmit and update anode plate information through an information carrier containing the anode plate's identification identifier. For example, in each process of the electrolysis production line, the corresponding operation information of the anode plate for that process can be written into the information carrier. Specifically, the casting process can write casting information, the shaping process can write shaping information, and the electrolysis process can write electrolysis information, etc.

[0096] In some embodiments, specific identity information can be stored in a database and associated with the anode plate. For example, the anode plate and its information stored in the database can be associated with the anode plate's identity identifier. When needed, specific information about the anode plate can be obtained by retrieving the corresponding information from the database based on the obtained identity identifier.

[0097] In some embodiments, during the casting process 160-1, the system can create corresponding identity information for each anode plate obtained by casting based on the acquired mineral source information and the casting information of the specific casting process (such as casting date, casting personnel, mold information, etc.), and save it in a barcode-readable information carrier, and set the information carrier on the anode plate.

[0098] In some embodiments, during the shaping process 160-2, the system can obtain the corresponding anode plate information by scanning the information carrier on each anode plate, and update the anode plate information based on the shaping information (e.g., shaping equipment process parameters, anode plate weight information, etc.). In some embodiments, the shaped anode plate information can be updated to a database or information carrier.

[0099] In some embodiments, during electrolysis step 160-3, the system can obtain the corresponding anode plate information by scanning the information carrier on the electrolytic cell, and update the anode plate information based on electrolysis information (e.g., electrolysis equipment process parameters, anode plate shape information, etc.). In some embodiments, the shaped anode plate information can be updated to a database or information carrier.

[0100] In some embodiments, the infrared detection module 150-3 can be used to acquire temperature information of the anode plate and / or cathode plate in each process. For example, the infrared detection module 150-3 (e.g., an infrared thermal imager) can perform infrared thermal imaging on the anode plate, receive infrared signals of a specific band from the thermal radiation of the anode plate, convert the signals into images and graphics that can be distinguished by human vision, and further calculate the temperature value of the anode plate.

[0101] In some embodiments, the anode plate temperature information obtained during the casting process can be used to determine whether the casting furnace is working properly and whether the casting formula is abnormal. For example, when the anode plate temperature is higher than 1400 degrees, it can be determined that the temperature setting of the casting furnace may be abnormal or the impurity content in the casting formula may exceed the standard.

[0102] In some embodiments, the infrared detection module 150-3 can perform infrared thermal imaging on the anode plates in each process and determine quality characteristic information based on the thermal imaging images.

[0103] In some embodiments, the temperature detection module 150-5 (e.g., a temperature sensor) can be used to acquire temperature information of the casting furnace, electrolytic cell, and anode plate. For example, the temperature detection module 150-5 may include multiple temperature sensors installed at different locations within the casting furnace to acquire the temperature at different locations within the furnace; or, for example, the temperature detection module 150-5 may include multiple temperature sensors installed at different locations within the electrolytic cell to acquire the temperature at different locations within the electrolyte or anode plate; or, for example, a temperature sensor installed in the electrolyte can be used to acquire the electrolyte temperature; or, for example, a temperature sensor installed on the surface of the anode plate can be used to acquire the anode plate temperature.

[0104] In some embodiments, excessively large temperature differences in the electrolyte at different locations within the electrolytic cell (e.g., a temperature difference greater than 1°C), or excessively low electrolyte temperatures, can lead to crystallization near the cathode plate, thereby affecting the quality of the metal produced by subsequent electrolysis. The electrolyte temperatures to be obtained may include at least two electrolyte temperatures measured at at least two different depths within the electrolytic cell, wherein the difference between the electrolyte temperatures measured at the two depths is the interlayer temperature difference of the electrolyte.

[0105] In some embodiments, the image acquisition module 150-4 (e.g., a camera, an image sensor, etc.) can be used to acquire image information of the anode plate in each process. For example, the image acquisition module 150-4 can acquire image information of the anode plate and perform image recognition to obtain information such as the color, texture, shape, and spatial relationship of the anode plate and / or cathode plate in each process of electrolysis production.

[0106] In some embodiments, the image information of the anode plates can be used to determine whether the casting formula, casting mold, or shaping equipment is abnormal. For example, if several anode plates are found to have missing corners, it can be determined that the casting mold may be abnormal.

[0107] Image recognition can include processing, analysis, and understanding to identify targets and objects in various patterns. For example, image acquisition module 150-4 can acquire images; preprocess the acquired images to remove irrelevant information, restore useful real information, enhance the detectability of relevant information, and simplify the data to the maximum extent; feature extraction can be performed on the preprocessed images, and algorithms such as Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP), and Haar-like features can be used to extract color features, texture features, shape features, and spatial relationship features of the anode plate and / or cathode plate.

[0108] In some embodiments, the ultrasonic testing module 150-6 (e.g., a pulse-echo ultrasonic flaw detector) can be used to collect surface quality characteristic information of the anode plate in each process (e.g., surface flatness, integrity, texture, and thickness uniformity of the anode plate).

[0109] In some embodiments, a laser device (e.g., a laser thickness gauge) can also be used to collect quality characteristic information of the anode plate in various processes. For example, the laser device can measure the thickness of the cathode plate and / or anode plate at different locations.

[0110] In some embodiments, the quality characteristic information of the anode plate can be used to determine whether the casting mold or the shaping equipment is abnormal. For example, if small pits are detected on the surface of the anode plate, it can be determined that the casting mold or the extrusion component of the shaping equipment may be abnormal. As another example, if uneven thickness of the anode plate is detected, it can be determined that the parameter settings or structure of the grinding component of the shaping equipment may be abnormal, or the casting mold may be abnormal.

[0111] In some embodiments, the sampling and testing module 150-7 can be used to randomly sample the anode plates in each process and analyze the chemical composition of the anode plates. For example, the sampling and testing module 150-7 can randomly sample the anode plates, drill holes to sample the electrolytically generated metal attached to the cathode plates, and perform chemical composition analysis on the samples; or, for example, the sampling and testing module 150-7 can sample particles on the surface of the cathode plates and / or anode plates for chemical composition analysis, for example, analyzing the purity and impurities of the metal products (e.g., copper), wherein the impurities include the type and content of the main impurities (e.g., silver and its content).

[0112] In some embodiments, the chemical composition information of the anode plate can be used to determine the casting temperature, casting formula ratio, or whether the ore source is abnormal. For example, if excessive sulfur content is detected in the anode plate, it can be determined that the quality of copper in the ore source may be problematic. Similarly, if excessive tin content is detected in the anode plate, it can be determined that the temperature inside the casting furnace may not have reached a reasonable range, resulting in incomplete oxidation.

[0113] In some embodiments, the manual inspection module 150-1, barcode scanning inspection module 150-2, infrared inspection module 150-3, image acquisition module 150-4, temperature inspection module 150-5, ultrasonic inspection module 150-6, sampling inspection module 150-7, and timing module 150-8 described above can also perform other functions. For example, the infrared inspection module 150-3 can also be used to obtain the position information of the anode plate. For instance, the infrared inspection module 150-3 can acquire infrared thermal images of the electrolytic cell using a thermal imager, process the infrared thermal images to obtain pixels of the anode plate with abnormal temperature, and finally determine the corresponding anode plate position based on these pixels.

[0114] In some embodiments, the data acquisition device 150 can acquire composition information of several anode plates to be evaluated; process the composition information based on a risk prediction model to obtain a risk prediction value indicating that the anode plate to be evaluated is abnormal. Further, the data acquisition device 150 can acquire production monitoring information for anode plates with risk prediction values ​​greater than a preset threshold based on the risk prediction values, and then acquire further production monitoring information for anode plates with significantly higher risk prediction values. See step 310 for an explanation of acquiring production monitoring information.

[0115] In some embodiments, the composition information of several anode plates to be evaluated can be obtained by a detector. For example, the data acquisition device 150 can use a metal composition analyzer to obtain the composition information of the anode plates to be evaluated.

[0116] In some embodiments, a risk prediction model can be used to analyze and process the composition information of several anode plates to be evaluated to obtain a risk prediction value for the anode plate to be evaluated being abnormal.

[0117] In some embodiments, the input data for the risk prediction model consists of compositional information for multiple anode plates. The output data of the risk prediction model is the predicted risk value for an anode plate to be evaluated as abnormal.

[0118] In some embodiments, the risk prediction model may be a convolutional machine learning model (CNN), a fully convolutional neural network (FCN) model, a generative adversarial network (GAN), a backpropagation (BP) machine learning model, a radial basis function (RBF) machine learning model, a deep belief network (DBN), an Elman machine learning model, or a combination thereof.

[0119] In some embodiments, the risk prediction model may be a graph neural network (GNN) model. The nodes of the GNN model are multiple anode plates, and the edges are lines connecting two nodes; for two nodes cast from the same mold or shaped by the same equipment, a line is formed. Node features may include the composition information of the anode plate, and edge features may include information about the casting mold or shaping equipment (e.g., mold number).

[0120] In some embodiments, the parameters of the risk prediction model can be obtained by training multiple labeled training samples. In some embodiments, multiple sets of training samples can be obtained, each set of training samples may include multiple training data and corresponding labels for the training data. The training data may include the composition information of several historically produced anode plates, and the labels for the training data may be manually labeled based on the composition information to indicate whether the anode plate corresponding to that composition information is normal, such as normal or abnormal.

[0121] The parameters of the initial risk prediction model can be updated by using multiple sets of training samples to obtain a well-trained risk prediction model.

[0122] In some embodiments, the parameters of the initial risk prediction model can be iteratively updated based on multiple training samples to ensure that the model's loss function meets preset conditions. For example, the loss function converges, or the loss function value is less than a preset value. When the loss function meets the preset conditions, the model training is complete, and a trained risk prediction model is obtained.

[0123] In some embodiments, when the predicted risk value of one or more anode plates exceeds a preset threshold, the data acquisition device 150 can acquire the production monitoring information of the corresponding one or more anode plates. The preset threshold can be set by electrolysis production personnel (e.g., experts, technicians, etc.) based on their past experience.

[0124] The methods described in some embodiments of this specification, by using the data relationship between anode plates produced by the same casting mold or shaping equipment to predict the risk of anode plates, can better pre-screen the objects of information acquisition, identify high-risk targets, and then collect further information on high-risk targets, thereby improving the effectiveness and efficiency of electrolytic production monitoring data acquisition and reducing the amount of data processing.

[0125] Figure 5 This is an exemplary flowchart illustrating the analysis of electrolytic production monitoring information 510 to determine electrolytic production improvement information 520, based on some embodiments of this specification.

[0126] Reference Figure 5 In some embodiments, the determining module 220 can analyze the electrolysis production monitoring information 510 to determine electrolysis production improvement information 520.

[0127] In some embodiments, the electrolytic production monitoring information 510 may include the casting detection information 510-1 of the anode plate, the electrolytic production improvement information 520 may include the electrolytic production parameters 520-1, and the determining module 220 may obtain the quality characteristics of the anode plate based on the electrolytic production monitoring information, and then determine the electrolytic production parameters 520-1 based on the difference between the quality characteristics of the anode plate and the standard characteristics. The electrolytic production parameters 520-1 include at least one of electrolyte ratio parameters and additive ratio parameters.

[0128] Understandably, the electrolyte ratio parameters can be adjusted based on the composition information of the anode plate. For example, if the copper content in the anode plate is high, the copper ion concentration in the electrolyte will be too high during electrolysis, thereby reducing the quality of copper deposited on the cathode plate (e.g., making the surface of the deposited copper on the cathode plate rough). Therefore, it is necessary to dilute with water (i.e., increase the proportion of water in the electrolyte). Conversely, if the copper content in the anode plate is low, the copper ion concentration in the electrolyte will be too low during electrolysis, thereby reducing the quality of copper deposited on the cathode plate (e.g., making the deposited copper on the cathode plate loose and prone to particle growth on the surface). Therefore, it is necessary to increase the copper ion concentration (e.g., increase the proportion of copper sulfate (CuSO4) solution).

[0129] The additive formulation parameters can be adjusted based on the composition information of the anode plate. For example, if the silver content of the anode plate is higher than a certain threshold, it may lead to a high anion concentration. In this case, hydrochloric acid can be added in appropriate amounts to generate AgCl, thereby causing silver ions to precipitate into the anode mud and reducing precious metal loss. More detailed information on casting testing, electrolyte formulation parameters, and additive formulation parameters can be found in [link to relevant documentation]. Figure 3 The details and related descriptions will not be repeated here.

[0130] The quality characteristics of the anode plate can be information related to the anode plate produced by the current casting, such as the composition information of the anode plate. In some embodiments, the determining module 220 can determine the quality characteristics of the anode plate based on casting inspection information.

[0131] Standard features can be quality characteristics of standard anode plates, such as composition information. Standard anode plates can be anode plates produced in historical castings that conform to preset standards; for example, anode plates produced in historical castings whose dimensions, weight, and composition all conform to preset standards. In some embodiments, the determining module 220 can obtain standard features from the storage device 140, the data acquisition device 150, or an external data source. In some embodiments, the determining module 220 can use the data acquisition device 150 to detect the anode plates to obtain standard features.

[0132] In some embodiments, the determining module 220 may determine at least one of the electrolyte ratio parameters and additive ratio parameters based on the difference between the composition information of the anode plate and the composition information of the standard anode plate.

[0133] In some embodiments, the determining module 220 can determine at least one of the electrolyte ratio parameters and additive ratio parameters based on the difference between the composition information of the anode plate and the composition information of the standard anode plate in various ways. For example, the determining module 220 can determine the electrolytic production parameter 520-1 based on the difference between the composition information of the anode plate and the composition information of the standard anode plate using historical data. The historical data may include the difference between the composition information of the anode plate and the composition information of the standard anode plate at at least one historical time point and the corresponding electrolytic production parameter 520-1.

[0134] For example, the copper content of the anode plate cast at historical time point A is 1% higher than that of the standard anode plate; the copper content of the anode plate cast at historical time point B is 3% higher than that of the standard anode plate; and the copper content of the anode plate cast at historical time point C is 1% lower than that of the standard anode plate. The difference between the composition information of the currently cast anode plate and the composition information of the standard anode plate is that the copper content of the currently cast anode plate is 0.5% higher than that of the standard anode plate. Therefore, the determining module 220 can select the electrolyte ratio parameters and additive ratio parameters corresponding to the anode plate cast at historical time point A with the closest difference value as the electrolyte ratio parameters and additive ratio parameters of the currently cast anode plate.

[0135] In some embodiments, the determining module 220 may determine at least one of the electrolyte ratio parameters and additive ratio parameters based on the composition information of the anode plate using human experience. For example, at least one of the electrolyte ratio parameters and additive ratio parameters may be determined by industry experts based on the composition information of the anode plate.

[0136] In some embodiments, the determining module 220 may determine the adjustment information of the electrolysis production parameters based on the difference between the composition information of the anode plate and the composition information of the standard anode plate, and then determine the electrolysis production parameters 520-1 based on the adjustment information.

[0137] Understandably, standard characteristics correspond to standard electrolysis production parameters, which may include at least one of standard electrolyte ratio parameters and standard additive ratio parameters. The adjustment information for electrolysis production parameters may be information related to adjusting standard electrolysis production parameters (e.g., standard electrolyte ratio parameters, standard additive ratio parameters, etc.) based on the quality characteristics of the anode plate, such as at least one of the standard electrolyte ratio adjustment amount and standard additive ratio adjustment amount.

[0138] In some embodiments, the determining module 220 can determine the adjustment information of electrolysis production parameters based on the difference between the composition information of the anode plate and the composition information of the standard anode plate, using human experience. For example, the adjustment information of electrolysis production parameters can be determined by industry experts based on the difference between the composition information of the anode plate and the composition information of the standard anode plate.

[0139] In some embodiments, the determining module 220 can determine adjustment information based on the difference between the composition information of the anode plate and the composition information of the standard anode plate using historical data. The historical data may include the difference between the composition information of the anode plate and the composition information of the standard anode plate at at least one historical time point, and the corresponding adjustment information. Taking historical time points A, B, and C as an example, the determining module 220 can select the adjustment information corresponding to the anode plate cast at historical time point A, which has the closest difference value, as the adjustment information for the currently cast anode plate.

[0140] In some embodiments, the determining module 220 can directly determine the adjustment information based on the fitted curve, wherein the fitted curve can characterize the changes in the adjustment information of electrolysis production parameters (e.g., the adjustment amount of electrolyte ratio and / or the adjustment amount of additive ratio, etc.) with the difference between quality characteristics and standard characteristics.

[0141] In some embodiments, the determining module 220 can obtain the correspondence between the difference between quality characteristics and standard characteristics and the adjustment information of electrolytic production parameters based on historical data and through multiple linear regression fitting. For example, the determining module 220 can establish the correspondence between the difference between quality characteristics and standard characteristics and the adjustment information of electrolytic production parameters based on a set of multiple linear regression equations. The independent variables of the multiple linear regression equations may include the difference between quality characteristics and standard characteristics, and the dependent variables of the multiple linear regression equations may include the adjustment information of electrolytic production parameters (e.g., the adjustment amount of electrolyte ratio and / or the adjustment amount of additive ratio, etc.).

[0142] In some embodiments, the determining module 220 can substitute the difference between quality characteristics and standard characteristics at at least one historical time point into the independent variables of the multiple linear regression equation system, and substitute the corresponding adjustment information of electrolytic production parameters into the dependent variables of the multiple linear regression equation system. The multiple linear regression equation system is solved based on the least squares method and other methods to obtain the correspondence between the difference between quality characteristics and standard characteristics and the adjustment information of electrolytic production parameters, and a fitting curve is generated based on the correspondence.

[0143] Understandably, when it is necessary to determine the adjustment information of the electrolysis production parameters, the determination module 220 can substitute the difference between the quality characteristics determined this time and the standard characteristics into the independent variables of the multiple linear regression equation system, thereby obtaining the adjustment information of the electrolysis production parameters.

[0144] In some embodiments, the correspondence between the difference between quality characteristics and standard characteristics and the adjustment information of electrolytic production parameters is fitted by multiple linear regression, so that the adjustment information of electrolytic production parameters determined based on the difference between quality characteristics and standard characteristics is more accurate.

[0145] In some embodiments, the determining module 220 can determine the adjustment information through an adjustment amount confirmation model. Further description of the adjustment amount confirmation model can be found in [reference needed]. Figure 7 The details and related descriptions will not be repeated here.

[0146] In some embodiments, the determining module 220 may adjust the standard electrolysis production parameters (e.g., standard electrolyte ratio parameters, standard additive ratio parameters, etc.) based on the adjustment information of the electrolysis production parameters.

[0147] For example, if the copper content of the anode plate is greater than that of the standard anode plate by 4%, the adjustment information for the electrolysis production parameters includes increasing the thiourea ratio from the standard ratio (e.g., 10 mg / L) to 15 mg / L, allowing the thiourea to fully react with the copper ions in the anode plate to form a complex, increasing the smoothness of the copper deposition surface. As another example, if the silver content of the anode plate is greater than that of the standard anode plate by 2%, the adjustment information for the electrolysis production parameters includes increasing the hydrochloric acid ratio from the standard ratio (e.g., 1%) to 2%. By appropriately increasing the amount of hydrochloric acid added, the silver ions in the anode plate are completely precipitated into the anode mud, reducing the loss of precious metals.

[0148] In some embodiments, the electrolysis production monitoring information 510 may include at least one of anode plate casting information 510-2 and shaping information 510-3. The electrolysis production improvement information 520 may include process improvement information 520-2 or anomaly handling scheme 520-3. The determining module 220 may determine production anomaly information based on the production monitoring information, and then determine process improvement information 520-2 or anomaly handling scheme 520-3 based on the production anomaly information. Further descriptions of the anode plate casting information 510-2, shaping information 510-3, process improvement information 520-2, and anomaly handling scheme 520-3 can be found in [reference needed]. Figure 3 The details and related descriptions will not be repeated here.

[0149] Production anomaly information can be related to processes that produce defective anode plates. For example, production anomaly information can be related to the casting and / or shaping processes of defective anode plates.

[0150] In some embodiments, the determining module 220 can determine unqualified anode plates based on production monitoring information, obtain characteristic information of unqualified anode plates, and then determine equipment abnormality information in the casting process and / or equipment abnormality information in the shaping process based on the characteristic information of unqualified anode plates.

[0151] In some embodiments, the determining module 220 can identify defective anode plates based on production monitoring information using human experience. For example, industry experts can identify defective anode plates based on production monitoring information.

[0152] The characteristic information of a defective anode plate can be information related to the defective anode plate. For example, the characteristic information of a defective anode plate can include its weight, shape, and composition.

[0153] Equipment anomaly information during the casting process can be related to abnormal equipment used in the casting of substandard anode plates. For example, equipment anomaly information during the casting process may include abnormal parameters of the casting furnace or casting mold.

[0154] In some embodiments, the determining module 220 can determine equipment abnormality information in the casting process from the production monitoring information based on the characteristic information of the defective anode plate. For example, the shape information of the defective anode plate includes: uneven surface. Then, the equipment abnormality information in the casting process may include abnormal parameters of the furnace that produces the defective anode plate in the production monitoring information, such as abnormal temperature of the furnace during the casting of the defective anode plate.

[0155] Equipment anomaly information in the shaping process can be related to abnormal equipment used in the shaping process of defective anode plates. For example, equipment anomaly information in the shaping process can include abnormal parameters of conveyor belts, pressure ears, grinding fixtures (e.g., milling cutters), etc.

[0156] In some embodiments, the determining module 220 can determine equipment abnormality information in the shaping process from the production monitoring information based on the characteristic information of the defective anode plate. For example, when the characteristic information of the defective anode plate includes the weight information and shape information of the defective anode plate, the determining module 220 can determine the equipment abnormality information in the shaping process from the production monitoring information, which may include: the model and working parameters (e.g., the pressure generated by the pressing ear) of the defective anode plate; the model and working parameters (e.g., the milling cutter speed) of the grinding tool (e.g., milling cutter) of the defective anode plate.

[0157] In some embodiments, the determining module 220 may determine the characteristic information of the anode plate to be evaluated based on production monitoring information, the characteristic information including at least one of composition characteristics, weight characteristics, and casting mold.

[0158] In some embodiments, the determining module 220 can predict whether the anode plate to be evaluated is qualified based on human experience, considering at least one of the following: composition characteristics, weight characteristics, and casting mold. For example, industry experts can predict whether the anode plate to be evaluated is qualified based on whether the anode plate to be evaluated is qualified.

[0159] In some embodiments, the determining module 220 can predict whether the anode plate to be evaluated is a qualified product based on at least one of the following: composition characteristics, weight characteristics, and casting mold, using preset evaluation rules. The preset evaluation rules can characterize the standards related to the composition characteristics, weight characteristics, and casting mold used to determine whether the anode plate is a qualified product. For example, the preset evaluation rules may include: the weight is between 2 kg and 3 kg; if the weight of the anode plate to be evaluated is less than 2 kg, the determining module 220 can determine that the anode plate to be evaluated is not a qualified product.

[0160] In some embodiments, the determining module 220 can predict whether the anode plate to be evaluated is a qualified product based on the historical characteristic information of multiple historically produced defective anode plates, which may include at least one of the composition characteristics, weight characteristics, and casting molds of the historically produced defective anode plates. For example, the determining module 220 can obtain the similarity between the characteristic information of the current anode plate (i.e., the anode plate to be evaluated) and the historical characteristic information of multiple historically produced defective anode plates, and use the similarity as the risk level of the defective product; based on the risk level, it can predict whether the anode plate to be evaluated is a qualified product.

[0161] In some embodiments, the determining module 220 can obtain the similarity between the feature information of the current anode plate and the historical feature information of previously produced defective anode plates through a similarity algorithm. The similarity algorithm may include at least one of Euclidean metric and cosine distance. For example, the determining module 220 can convert the feature information of the current anode plate into a first vector and convert the historical feature information of multiple previously produced defective anode plates into multiple second vectors, and then determine the similarity between the first vector and each second vector based on cosine distance.

[0162] Understandably, the determining module 220 can determine the risk level of the current anode plate's non-conforming product based on the similarity between the current anode plate's characteristic information and the historical characteristic information of each historically produced non-conforming anode plate. For example, the determining module 220 can use the average similarity between the current anode plate's characteristic information and the historical characteristic information of each historically produced non-conforming anode plate as the risk level of the current anode plate's non-conforming product. In some embodiments, anode plates to be evaluated with a risk level greater than a preset risk level threshold are considered non-conforming products.

[0163] In some embodiments, the determining module 220 can acquire feature information of anode plates predicted to be unqualified, and predict at least one of equipment mold anomaly information, ore blending anomaly information, and batch of unqualified products prediction information based on the feature information of the unqualified anode plates. The batch of unqualified products can be anode plates produced using the same ore blending, casting equipment (e.g., furnace, mold, etc.) and / or shaping equipment (e.g., pressure ear, milling cutter, etc.) as the unqualified anode plate. For example, when the antimony impurity content of the unqualified anode plate is high, the determining module 220 can predict that there is an anomaly in the ore blending and can predict that all anode plates produced in the same batch as the unqualified anode plate are unqualified. As another example, when the thickness of the unqualified anode plate is abnormal, the determining module 220 can predict that the mold model is abnormal and can predict that all anode plates produced in the same batch as the unqualified anode plate are unqualified.

[0164] In some embodiments, the determining module 220 can predict at least one of the following based on the characteristic information of the non-conforming anode plate: equipment mold abnormality information, ore blending abnormality information, and batch non-conforming product prediction information, using human experience.

[0165] In some embodiments, the determining module 220 can predict at least one of the following based on the feature information of the defective anode plate: equipment mold abnormality information, ore blending abnormality information, and batch defective product prediction information, using a machine learning model.

[0166] In some embodiments, the determining module 220 can predict the probability of equipment mold abnormality based on the feature information of the defective anode plate using a first prediction model. The input of the first prediction model can be the feature information of the defective anode plate, and the output of the first prediction model can be the probability of predicting equipment mold abnormality.

[0167] In some embodiments, the determining module 220 can predict the probability of equipment mold abnormality based on the feature information of the unqualified anode plate using a second prediction model. The input of the second prediction model can be the feature information of the unqualified anode plate, and the output of the second prediction model can be the probability of ore blending abnormality.

[0168] In some embodiments, the determining module 220 can predict equipment mold abnormality information based on the feature information of unqualified anode plates using a third prediction model. The input of the third prediction model can be the feature information of unqualified anode plates, and the output of the third prediction model can be the probability that the anode plates in the same batch are unqualified.

[0169] In some embodiments, the determining module 220 can train the initial first prediction model, the initial second prediction model, and / or the initial third prediction model using multiple labeled training samples. Each training sample corresponds to a historically produced defective anode plate. The training sample may include feature information of the historically produced anode plate, and the label of the training sample may include the anomaly information corresponding to the historically produced anode plate (e.g., whether the equipment mold is abnormal, whether the ore blending is abnormal, and whether the products produced in the same batch are defective).

[0170] In some embodiments, the determining module 220 can train the initial first prediction model, the initial second prediction model, and / or the initial third prediction model multiple times using common methods (e.g., gradient descent) until the trained initial first prediction model, the initial second prediction model, and / or the initial third prediction model meet preset conditions. The trained initial first prediction model is then used as the first prediction model for predicting equipment mold anomaly information, the trained initial second prediction model is used as the second prediction model for predicting ore blending anomaly information, and / or the trained initial third prediction model is used as the third prediction model for predicting non-conforming products in the same batch. The preset conditions may be that the loss function of the updated initial first prediction model, the initial second prediction model, and / or the initial third prediction model is less than a threshold, converges, or the number of training iterations reaches a threshold.

[0171] In some embodiments, the first prediction model, the second prediction model, and / or the third prediction model may also be pre-trained by the server 110 or a third party and stored in the storage device 140, and the determination module 220 may directly call the first prediction model, the second prediction model, and / or the third prediction model from the storage device 140.

[0172] In some embodiments, the first prediction model, the second prediction model, and the third prediction model may include, but are not limited to, one or more combinations of neural networks (NN), decision trees (DT), linear regression (LR), etc.

[0173] In some embodiments, the determining module 220 may determine process improvement information 520-2 or anomaly handling plan 520-3 based on production anomaly information.

[0174] In some embodiments, the determining module 220 may determine process improvement information 520-2 or anomaly handling plan 520-3 based on production anomaly information using human experience. For example, industry experts may determine process improvement information 520-2 or anomaly handling plan 520-3 based on production anomaly information.

[0175] In some embodiments, the determining module 220 may determine process improvement information 520-2 or anomaly handling scheme 520-3 based on production anomaly information based on a preset adjustment rule table. The preset adjustment rule table may be used to record preset adjustment rules, which may characterize the correspondence between production anomaly information and process improvement information 520-2 or anomaly handling scheme 520-3.

[0176] For example, preset adjustment rules may include: when related equipment malfunctions, suspending the related equipment and performing maintenance; if defective anode plates are found, reprocessing the anode plates produced in the same batch as the defective ones. Understandably, the determining module 220 can search for process improvement information 520-2 or anomaly handling plan 520-3 from the preset adjustment rule table based on production anomaly information. For instance, the determining module 220 obtains keywords based on production anomaly information and searches for process improvement information 520-2 or anomaly handling plan 520-3 from the preset adjustment rule table based on these keywords.

[0177] In some embodiments, the determining module 220 can determine the anomaly type by processing the abnormal parameters of the anode plate using an anomaly determination model. More details about the anomaly determination model can be found in [reference needed]. Figure 10 The details and related descriptions will not be repeated here.

[0178] In some embodiments, the determining module 220 can obtain process parameter adjustment information by processing production monitoring information through a third model. The process parameter adjustment information includes casting process adjustment parameters or shaping process adjustment parameters. Casting process adjustment parameters can be parameters for adjusting the casting process of producing defective anode plates, such as furnace temperature adjustment parameters, mold type adjustment parameters, casting formula adjustment parameters, etc. Shaping process adjustment parameters can be parameters for adjusting the shaping process of producing defective anode plates, such as pressure adjustment parameters for the pressure lugs, milling cutter speed adjustment parameters, etc.

[0179] The third model can be a machine learning model used to determine process parameter adjustment information. The input to the third model can be production monitoring information, and the output of the third model can be process parameter adjustment information.

[0180] In some embodiments, the determining module 220 can train the initial third model using multiple labeled training samples, wherein each training sample corresponds to a historically produced anode plate, the training sample may include production monitoring information of the historically produced anode plate, and the label of the training sample may include process parameter adjustment information corresponding to the historically produced anode plate.

[0181] In some embodiments, the determining module 220 may train the initial third model multiple times using common methods (e.g., gradient descent) until the trained initial third model meets preset conditions, and then use the trained initial third model as the third model for predicting process parameter adjustment information. The preset conditions may be that the loss function of the updated initial third model is less than a threshold, convergence, or the number of training iterations reaches a threshold.

[0182] In some embodiments, the third model may also be pre-trained by the server 110 or a third party and stored in the storage device 140, and the determination module 220 may directly call the third model from the storage device 140.

[0183] In some embodiments, the third model may include, but is not limited to, one or more combinations of neural networks (NN), decision trees (DT), linear regression (LR), etc.

[0184] In some embodiments, by processing production monitoring information through a third model, process parameter adjustment information can be obtained quickly and accurately.

[0185] In some embodiments, the determining module 220 can acquire feature information of anode plates predicted to be unqualified, process the feature information of the unqualified anode plates based on the fourth model, and predict the disposal costs of different disposal methods, wherein the disposal methods include at least one of settling and remelting. In some embodiments, the determining module 220 can detect the unqualified anode plates through the data acquisition device 150 to obtain feature information of the unqualified anode plates. For example, the determining module 220 can obtain the shape information of the unqualified anode plates through the ultrasonic detection module 150-6.

[0186] The fourth model can be a machine learning model used to determine process parameter adjustment information. The input of the fourth model can be the feature information of defective anode plates, and the output of the fourth model can be the treatment cost of different treatment methods.

[0187] The training and model structure of the fourth model are similar to those of the third model. For more details on the training and model structure of the fourth model, please refer to the relevant description of the third model. It is understood that the training samples used to train the fourth model include the feature information of a historically produced defective anode plate. The training samples may include the feature information of historically produced defective anode plates, and the labels of the training samples may include the disposal costs of different disposal methods.

[0188] In some embodiments, the determining module 220 may determine the disposal method for nonconforming products based on the predicted disposal cost. For example, the determining module 220 may choose the disposal method corresponding to the minimum predicted disposal cost as the disposal method for nonconforming products.

[0189] In some embodiments, by processing the feature information of non-conforming anode plates based on the fourth model, the disposal costs of different disposal methods can be quickly predicted, so as to determine the appropriate disposal method for non-conforming products and reduce the cost of disposing of non-conforming products.

[0190] Figure 6 This is an exemplary flowchart illustrating the improvement of electrolysis production processes based on electrolysis production improvement information, according to some embodiments of this specification.

[0191] like Figure 6 As shown, in some embodiments, the improvement module 230 can improve the electrolysis production process 620 based on the electrolysis production improvement information 610. For example, the improvement module 230 can acquire at least one of the following in the electrolysis production process: improvement information of process parameters, prediction information of defective products, traceability information of production anomalies, and disposal information of defective products, and improve at least one of the following processes: anode plate casting process, shaping process, disposal of defective products, and electrometallurgical process, based on the above information.

[0192] In some embodiments, the improvement module 230 may improve the casting and / or shaping process of the anode plate based on the improvement information of process parameters in the electrolysis production process and / or the traceability information of production anomalies.

[0193] For example, the improvement module 230 can set the furnace temperature based on the improved furnace operating temperature. As another example, the improvement module 230 can change the ore source based on production anomaly traceability information, manually destroy abnormal ore raw materials according to the ore source ratio, and evaluate and rank suppliers based on the electrode plate qualification rate produced from the ore supplied by the suppliers, prioritizing suppliers with higher electrode plate qualification rates. As another example, the improvement module 230 can generate automatic prompts for the periodic inspection, maintenance, and replacement of casting molds for producing substandard anode plates based on production anomaly traceability information. As yet another example, the improvement module 230 can generate different levels of alarm prompts (including text, voice, flashing alarm lights, buzzers, etc.) based on production anomaly traceability information. The improvement module 230 can also switch the shaping method from extrusion to grinding based on the improvement information of process parameters in the electrolysis production process.

[0194] In some embodiments, the improvement module 230 can adjust the electrometallurgical process parameters based on improvement information of process parameters in the electrolysis production process. For example, the improvement module 230 can control the relevant equipment to prepare the electrolyte according to the electrolysis production parameters, and can also control the relevant equipment to add at least one additive to the prepared electrolyte.

[0195] In some embodiments, the improvement module 230 can process the predicted non-conforming anode plates based on the prediction information of non-conforming products. For example, the improvement module 230 can notify relevant personnel to manually inspect the predicted non-conforming products based on the prediction information of non-conforming products.

[0196] In some embodiments, the improved module 230 can dispose of non-conforming products based on their disposal information. For example, the improved module 230 can control relevant equipment or personnel to set the non-conforming anode plates idle or remelt them based on the disposal information.

[0197] The methods described in some embodiments of this specification, by improving the electrolysis production process based on electrolysis production improvement information, can effectively reduce the generation of defective products and ensure the effective operation of the electrolysis production process. For example, by improving the casting and / or shaping processes of anode plates through improvement information on process parameters and / or traceability information of production anomalies in the electrolysis production process, the anode plates produced subsequently are more in line with requirements. Another example is that by adjusting the electrometallurgical process parameters through improvement information on process parameters in the electrolysis production process, the quality of the metal precipitated by electrometallurgy can be improved. Yet another example is that by processing predicted defective anode plates based on defective product prediction information, the number of anode plates that operators need to inspect can be reduced, allowing for the rapid identification of other defective anode plates. Furthermore, by disposing of defective products based on defective product disposal information, defective anode plates can be disposed of, preventing them from entering the electrometallurgical process and causing further waste of electrolytic raw materials (e.g., electrolytic cells, electrolytes, etc.), thereby minimizing cost waste caused by defective products.

[0198] like Figure 7 As shown, in some embodiments, the determining module 220 can determine the difference vector 710 between the quality characteristics and the standard characteristics, and based on the difference vector 710, determine the adjustment information of the electrolysis production parameters through the adjustment amount confirmation model 720. The adjustment information of the electrolysis production parameters may include an electrolyte ratio adjustment amount 730 and / or an additive ratio adjustment amount 740.

[0199] Quality characteristics and standard characteristics can be represented by feature vectors. Each element in the feature vector of a quality characteristic represents a characteristic of the anode plate, such as the content of a certain component in the anode plate. Each element in the feature vector of a standard characteristic represents a characteristic of the standard anode plate, such as the content of a certain component in the anode plate.

[0200] The difference vector 710 between the quality feature and the standard feature can be the difference between the feature vector corresponding to the quality feature and the feature vector corresponding to the standard feature.

[0201] The adjustment amount confirmation model 720 can be a machine learning model used to determine the electrolyte ratio adjustment amount 730 and / or the additive ratio adjustment amount 740. The input of the adjustment amount confirmation model 720 can be the difference vector 710 between the quality feature and the standard feature, and the output of the adjustment amount confirmation model 720 can be the electrolyte ratio adjustment amount 730 and / or the additive ratio adjustment amount 740.

[0202] The training and model structure of the adjustment amount confirmation model 720 are similar to those of the third model. For more details on the training and model structure of the adjustment amount confirmation model 720, please refer to the relevant description of the third model. It is understood that the training samples used to train the adjustment amount confirmation model 720 include the difference vector between the quality characteristics and standard characteristics of a historically produced anode plate. The training samples may include the feature information of historically produced non-conforming anode plates. The labels of the training samples may include the electrolyte ratio adjustment amount and / or the additive ratio adjustment amount.

[0203] The methods described in some embodiments of this specification, through the adjustment confirmation model 720, can quickly and accurately determine the adjustment information of electrolytic production parameters based on the difference between the quality characteristics and standard characteristics of the anode plate.

[0204] Reference Figure 8 In some embodiments, the adjustment amount confirmation model 820 may include a first adjustment amount confirmation model 821 and / or a second adjustment amount confirmation model 822.

[0205] The first adjustment amount confirmation model 821 can be a machine learning model for determining the electrolyte ratio adjustment amount 830. In some embodiments, the input of the first adjustment amount confirmation model 821 can be the difference vector 810 between the quality feature and the standard feature, and the output of the first adjustment amount confirmation model 821 can be the electrolyte ratio adjustment amount 830.

[0206] The second adjustment amount confirmation model 822 can be a machine learning model for determining the additive ratio adjustment amount 840. In some embodiments, the input of the second adjustment amount confirmation model 822 can be the difference vector between the quality feature and the standard feature, and the output of the second adjustment amount confirmation model 822 can be the additive ratio adjustment amount 840.

[0207] The training and model structure of the first adjustment amount confirmation model 821 and the second adjustment amount confirmation model 822 are similar to those of the third model. For more details on the training and model structure of the first adjustment amount confirmation model 821 and the second adjustment amount confirmation model 822, please refer to the relevant description of the third model. It is understood that the training samples used to train the first adjustment amount confirmation model 821 include the difference vector between the quality characteristics and standard characteristics of a historically produced anode plate. The training samples may include the feature information of historically produced defective anode plates, and the labels of the training samples may include the electrolyte ratio adjustment amount. The training samples used to train the second adjustment amount confirmation model 822 include the difference vector between the quality characteristics and standard characteristics of a historically produced anode plate. The training samples may include the feature information of historically produced defective anode plates, and the labels of the training samples may include the additive ratio adjustment amount.

[0208] The methods described in some embodiments of this specification, which determine the electrolyte ratio adjustment amount 830 and the additive ratio adjustment amount 840 through two independent models, can make the structure of each model simpler and reduce the workload of model training.

[0209] Reference Figure 9 In some embodiments, the adjustment amount confirmation model 920 may include a first adjustment amount confirmation model 921 and a second adjustment amount model 922.

[0210] The first adjustment amount confirmation model 921 can be a machine learning model for determining the electrolyte ratio adjustment amount. In some embodiments, the input of the first adjustment amount confirmation model 921 can be the difference vector 910 between the quality feature and the standard feature, and the output of the first adjustment amount confirmation model 921 can be the electrolyte ratio adjustment amount 930.

[0211] The second adjustment amount confirmation model 922 can be a machine learning model for determining the additive ratio adjustment amount. In some embodiments, the input of the second adjustment amount confirmation model 922 may include the difference vector 910 between the quality feature and the standard feature and the electrolyte ratio adjustment amount 930 output by the first adjustment amount confirmation model 921, and the output of the second adjustment amount confirmation model 922 may be the additive ratio adjustment amount 940.

[0212] In some embodiments, the parameters of the first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922 can be jointly trained. For example, the samples for joint training include the difference vector 910 between historical quality features and standard features, and the labels include historical additive ratio adjustment amounts. The difference vector 910 between historical quality features and standard features is input into the first adjustment amount confirmation model 921, and the output of the first adjustment amount confirmation model 921 is input into the second adjustment amount confirmation model 922. The output of the second adjustment amount confirmation model 922 and the labels are used to construct a loss function, and the parameters of the first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922 are updated simultaneously based on the loss function, resulting in the trained first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922.

[0213] In some embodiments, the first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922 may also be pre-trained by the server 110 or a third party and stored in the storage device 140, and the determination module 220 may directly call the first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922 from the storage device 140.

[0214] In some embodiments, the first adjustment confirmation model 921 and the second adjustment confirmation model 922 may be one or more combinations of neural networks (NN), decision trees (DT), linear regression (LR), etc.

[0215] The methods described in some embodiments of this specification, through joint training to obtain a first adjustment amount confirmation model 921 and a second adjustment amount confirmation model 922, simplify model training, save model training time, reduce the workload of model training, and reduce the total number of steps in training multiple models. In addition, it can solve the problem that historical electrolyte ratio adjustment amounts are not easy to obtain as tags, and when determining the additive ratio adjustment amount through the second adjustment amount confirmation model 922, the electrolyte ratio adjustment amount is also considered, avoiding duplicate adjustments of the electrolyte ratio adjustment amount and the additive ratio adjustment amount, which would increase the error. For example, if the sulfur content of the anode plate produced this time is less than that of the standard anode plate, and the electrolyte ratio adjustment amount and the additive ratio adjustment amount are determined by two independent machine learning models, the final determined electrolyte ratio adjustment amount is to increase the sulfuric acid solution by 1% and the additive ratio adjustment amount is to increase the thiourea by 1%, which results in an excessive addition of sulfur ions. However, if the electrolyte ratio adjustment amount determined by the first adjustment amount confirmation model 921 and the second adjustment amount confirmation model 922 is to increase the sulfuric acid solution by 1% and the additive ratio adjustment amount is to increase the thiourea by 0.5%, which results in an appropriate addition of sulfur ions.

[0216] In some embodiments, the determining module 220 can determine the final adjustment information based on adjustment information determined by fitting a curve (i.e., first adjustment information) and adjustment information determined by an adjustment amount confirmation model (i.e., second adjustment information). For example, the determining module 220 can perform a weighted sum of the first adjustment information and the second adjustment information to determine the final adjustment information. For instance, the determining module 220 can perform a weighted sum of the electrolyte ratio adjustment amount of the first adjustment information and the electrolyte ratio adjustment amount of the second adjustment information to determine the final electrolyte ratio adjustment amount. As another example, the determining module 220 can perform a weighted sum of the additive ratio adjustment amount of the first adjustment information and the additive ratio adjustment amount of the second adjustment information to determine the final additive ratio adjustment amount.

[0217] The methods described in some embodiments of this specification, by fusing adjustment information obtained in multiple ways, can make the final determined adjustment information more accurate. At the same time, when the adjustment information obtained in a certain way has a large error, it avoids directly using the adjustment information with a large error to adjust the electrolyte ratio and additive ratio.

[0218] Figure 10 This is an exemplary flowchart illustrating how an anomaly determination model, as shown in some embodiments of this specification, determines adjustment information for electrolysis production parameters.

[0219] In some embodiments, determining production anomaly information based on the production monitoring information may include: determining abnormal parameters of the anode plate based on the production monitoring information; processing the abnormal parameters of the anode plate based on the anomaly determination model to determine the anomaly type, wherein the anomaly type includes at least one of mold anomaly, casting parameter anomaly, and ore source anomaly.

[0220] The anomaly determination model 1020 can analyze and process the abnormal parameters 1010 of the input anode plate (such as high impurity content, abnormal verticality of the plate surface, etc.) and output the corresponding anomaly type (such as mold anomaly, casting parameter anomaly, ore source anomaly).

[0221] In some embodiments, the anomaly determination model 1020 may include various models and structures. In some embodiments, the machine learning model may include, but is not limited to, one or more combinations of neural networks (NN), decision trees (DT), linear regression (LR), etc.

[0222] In some embodiments, the abnormal parameters 1010 of one or more anode plates can be used as input to the anomaly determination model 1020. The output of the anomaly determination model 1020 can be an anomaly type. For example, if the plate dimensions of several anode plates are smaller than standard dimensions, the output anomaly type: mold anomaly.

[0223] In some embodiments, the abnormal parameters 1010 of the anode plates obtained at different time periods (e.g., morning, noon, evening, etc.) can be used as a sequence as the input of the anomaly determination model 1020, and the anomaly type 1030 corresponding to the abnormal parameters 1010 of each anode plate at different time periods can be used as the output of the anomaly determination model 1020.

[0224] The parameters of the anomaly determination model 1020 can be obtained through training. In some embodiments, multiple sets of training samples can be obtained based on a large amount of anode plate production data with anomalies. Each set of training samples can include multiple training data and corresponding labels. The training data can include anomalous parameters of the anode plates, and the labels can be historical anomaly types obtained based on historical anode plate anomaly parameters. For example, anomalous parameters of the anode plates at multiple time points within a period of time (such as one day, one week, one month, etc.) can be collected as training data to obtain the anomaly type determination results of the anode plate anomaly parameters (e.g., anomaly types directly labeled by humans based on the anomaly parameters).

[0225] In some embodiments, the parameters of the anomaly determination model 1020 can be iteratively updated based on multiple training samples to ensure that the model's loss function meets preset conditions. For example, the loss function converges, or the loss function value is less than a preset value. When the loss function meets the preset conditions, the model training is complete, and the trained anomaly determination model 1020 is obtained.

[0226] In some embodiments, the above-described determination of anomaly types based on anode plate anomaly parameters can also be implemented in other ways. For example, the determination module 220 can record historical anode plate anomaly parameters and their corresponding anomaly types. Based on the actual obtained anode plate anomaly parameters (e.g., anode plate verticality greater than 20%), it can query the corresponding anomaly types (e.g., casting mold deformation, pressure ear failure, etc.) in the historical anode plate anomaly parameter data to obtain one or more anomaly types corresponding to the current anode plate anomaly parameters. For another example, after obtaining the anode plate anomaly parameters (e.g., high antimony impurity content), electrolysis production personnel (e.g., experts, technicians, etc.) can rely on their past experience to determine one or more anomaly types (e.g., abnormal composition ratio, abnormal ore source, etc.).

[0227] The methods described in some embodiments of this specification can quickly identify abnormality types by analyzing abnormal parameters of the anode plate, which can improve production efficiency to a certain extent and avoid losses in subsequent production.

[0228] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0229] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0230] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0231] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0232] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0233] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with this specification, as well as documents that limit the broadest scope of the claims in this specification (attached to this specification hereafter). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0234] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for monitoring anomalies in electrolysis production, comprising: Obtain production monitoring information; The production monitoring information includes at least one of anode plate casting information and shaping information. The casting information includes composition information and casting mold, and the shaping information includes shaping inspection information. Obtaining the production monitoring information includes: The composition information of several anode plates to be evaluated is obtained using a detector; The risk prediction model is used to analyze and process the component information of the several anode plates to be evaluated, and obtain the risk prediction value that the anode plate to be evaluated is abnormal. The risk prediction model is a graph neural network model. The features of the nodes of the risk prediction model include the component information of the anode plate, and the features of the edges include the casting mold or the shaping detection information. In response to the risk prediction value of one or more anode plates being greater than a preset threshold, the production monitoring information of the corresponding one or more anode plates is obtained; Based on the production monitoring information, production anomaly information is determined, including: Based on the production monitoring information, abnormal parameters of the anode plate are determined; Based on the anomaly determination model, the abnormal parameters of the anode plate are processed to determine the anomaly type, which includes at least one of mold anomaly, casting parameter anomaly, and ore source anomaly. Based on the production anomaly information, process improvement information or anomaly handling solutions are determined.

2. The method according to claim 1, wherein determining the production anomaly information based on the production monitoring information includes: Based on the production monitoring information, the characteristic information of the anode plate to be evaluated is determined, and the characteristic information includes at least one of the following: composition characteristics, weight characteristics, and the casting mold. Based on the characteristic information of the anode plate to be evaluated, predict whether the anode plate to be evaluated is a qualified product.

3. The method according to claim 2, wherein determining whether the anode plate to be evaluated is a qualified product based on the characteristic information of the anode plate to be evaluated includes: The similarity between the two is obtained by matching the feature information of the current anode plate with the historical feature information of multiple historically produced defective anode plates. Using similarity as a measure of the risk of defective products; Based on the risk level, it is predicted whether the anode plate to be evaluated is a qualified product.

4. An anomaly monitoring system for electrolysis production, comprising: The acquisition module is used to acquire production monitoring information; The production monitoring information includes at least one of anode plate casting information and shaping information. The casting information includes composition information and casting mold, and the shaping information includes shaping inspection information. Obtaining the production monitoring information includes: The composition information of several anode plates to be evaluated is obtained using a detector; The risk prediction model is used to analyze and process the component information of the several anode plates to be evaluated, and obtain the risk prediction value that the anode plate to be evaluated is abnormal. The risk prediction model is a graph neural network model. The features of the nodes of the risk prediction model include the component information of the anode plate, and the features of the edges include the casting mold or the shaping detection information. In response to the risk prediction value of one or more anode plates being greater than a preset threshold, the production monitoring information of the corresponding one or more anode plates is obtained; The first determining module is used to determine production anomaly information based on the production monitoring information, including: Based on the production monitoring information, abnormal parameters of the anode plate are determined; Based on the anomaly determination model, the abnormal parameters of the anode plate are processed to determine the anomaly type, which includes at least one of mold anomaly, casting parameter anomaly, and ore source anomaly. The second determining module is used to determine process improvement information or anomaly handling plan based on the production anomaly information.

5. The system according to claim 4, wherein the first determining module is further configured to: Based on the production monitoring information, the characteristic information of the anode plate to be evaluated is determined, and the characteristic information includes at least one of the following: composition characteristics, weight characteristics, and the casting mold. Based on the characteristic information of the anode plate to be evaluated, predict whether the anode plate to be evaluated is a qualified product.

6. The system according to claim 5, wherein the first determining module is further configured to: The similarity between the current anode plate and the historical feature information of multiple historically produced defective anode plates is obtained by matching the feature information of the current anode plate with the historical feature information of the two. The similarity is used as the risk level of non-conforming products; Based on the risk level, it is predicted whether the anode plate to be evaluated is a qualified product.

7. An anomaly monitoring device for electrolytic production, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is configured to execute at least a portion of the computer instructions to implement the method as described in any one of claims 1 to 3.

8. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 3.

Images