CN114326648B

CN114326648B - Remote cooperative electrolysis control method and system

Info

Publication number: CN114326648B
Application number: CN202210035417.6A
Authority: CN
Inventors: 林建平; 胡夏斌; 林建灶; 叶栋; 徐关峰
Original assignee: Hangzhou Sanal Environmental Technology Co ltd
Current assignee: Hangzhou Sanal Environmental Technology Co ltd
Priority date: 2021-10-13
Filing date: 2021-10-13
Publication date: 2023-05-26
Anticipated expiration: 2041-10-13
Also published as: CN114326648A; CN115963784A

Abstract

The embodiment of the specification discloses a remote cooperative electrolysis control system and method. The system comprises: the data acquisition unit is used for acquiring electrolysis data, wherein the electrolysis data comprises field inspection data and equipment production data corresponding to the field inspection data based on time; the data transmission unit is used for transmitting the electrolysis data to a target command center, and the distance between the target command center and the site exceeds a threshold value; and the production control unit is used for controlling the production process of the site based on the guidance opinions acquired from the target command center.

Description

Remote cooperative electrolysis control method and system

Description of the division

The present application is a divisional application of chinese patent application 202111192666.8 entitled "a remote coordinated electrolysis control method and system" filed on day 10 and 13 of 2021.

Technical Field

The specification relates to the field of electrolysis, and in particular relates to a remote collaborative electrolysis control system.

Background

Electrolytic processes are commonly used in the field of sheet metal manufacturing. In order to ensure the quality of the metal sheet, it is necessary to strictly control the electrolytic process parameters such as the temperature of the electrolytic tank, the concentration of the electrolyte, the circulation amount of the electrolyte, etc. However, in the production process, errors are inevitably generated in manual operation, so that the product quality is affected. In addition, because the uncontrollable factors of the electrolysis process are more, the method often needs an experiential expert to conduct guidance, but expert resources are short, the consultation time is passive, and the production period is influenced.

It is therefore desirable to provide a remote coordinated electrolysis control system that allows accurate control of the electrolysis process while at the same time rationally utilizing expert resources.

Disclosure of Invention

One aspect of embodiments of the present description provides a remote coordinated electrolysis control system, the system comprising: the data acquisition unit is used for acquiring electrolysis data, wherein the electrolysis data comprise field inspection data and equipment production data corresponding to the field inspection data based on time; the data transmission unit is used for transmitting the electrolysis data to a target command center, and the distance between the target command center and the site exceeds a threshold value; and the production control unit is used for controlling the production process of the site based on the guidance opinions acquired from the target command center.

Another aspect of embodiments of the present specification provides a method of remote coordinated electrolysis control, the method comprising: the method comprises the steps of obtaining electrolysis data, wherein the electrolysis data comprise field inspection data and equipment production data corresponding to the field inspection data based on time; the electrolysis data are sent to a target command center, and the distance between the target command center and the site exceeds a threshold value; controlling the production process of the site based on the guidance opinions obtained from the target command center.

Another aspect of the present description provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement a method of remote coordinated electrolysis control.

Another aspect of the present description provides a device for remote coordinated electrolysis control, characterized in that the device comprises at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement a method of remote coordinated electrolysis control.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a schematic illustration of an application scenario of a remote coordinated electrolysis control system according to some embodiments of the present disclosure;

FIG. 2 is a schematic diagram of an apparatus of a remote coordinated electrolysis control system according to some embodiments of the present disclosure;

FIG. 3 is an exemplary schematic diagram of a remote coordinated electrolysis control system according to some embodiments of the present disclosure;

FIG. 4 is an exemplary flow chart for obtaining at least one update issue type according to some embodiments of the present description;

fig. 5 is an exemplary schematic diagram of a production control unit shown according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It should be appreciated that "system," "apparatus," "unit," and/or "module" as used in this specification is a method for distinguishing between different components, elements, parts, portions, or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic diagram of an application scenario 100 of a remote coordinated electrolysis control system according to some embodiments of the present description.

The remote cooperative electrolysis control system not only can control the dosage of the additive more accurately in production, but also can reasonably utilize expert resources, reduce the expert consultation cost and solve the problem of shortage of the expert, thereby optimizing the production process and improving the quality and the yield of the product.

In some embodiments, the application scenario 100 of the remote collaborative electrolytic control system includes a target command center 110, a processing device 120, AR glasses 130, an automation control system 140, a network 150, and a storage device 160.

The target command center 110 is a platform for remotely guiding the electrolysis process. In some embodiments, the target command center 110 may include an expert group 112 and one or more terminal devices 114 used by the expert group. Expert group 112 may include advanced technicians, researchers, etc. in various fields related to the electrolytic process. In some embodiments, the expert group may use the terminal device 114 to communicate with the processing device 120, the AR glasses 130, and/or the automated control system 140 over the network 150. For example, the expert group 112 may use the terminal device 114 to obtain electrolysis data from the AR glasses 130 and/or the automated control system 140. For another example, the expert group 112 may send the instructional opinion to the processing device 120 using the terminal device 114. In some embodiments, the terminal device 114 may be a desktop computer 114-1, a laptop computer 114-2, a mobile device 114-3, a tablet computer 114-4, other input and/or output enabled devices, and the like, or any combination thereof. The above examples are only intended to illustrate the broad scope of the terminal device and not to limit its scope.

The processing device 120 may be used to process data and/or information from at least one component of the application scenario 100 or an external data source (e.g., a cloud data center). For example, the processing device 120 may control the production process at the site based on the instructional opinion obtained from the target command center. In some embodiments, processing device 120 may comprise a single server or a group of servers. The server farm may be centralized or distributed (e.g., the processing device 120 may be a distributed system), may be dedicated, or may be serviced concurrently by other devices or systems. In some embodiments, the processing device 120 may be regional or remote. In some embodiments, the processing device 120 may be implemented on a cloud platform or provided in a virtual manner. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

Storage device 160 may be used to store data (e.g., field inspection data, equipment production data, etc.) and/or instructions. Storage device 160 may include one or more storage components, each of which may be a separate device or may be part of another device. In some embodiments, the storage device 160 may include Random Access Memory (RAM), read Only Memory (ROM), mass storage, removable memory, volatile read-write memory, and the like, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state disks, and the like. In some embodiments, storage device 160 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof. In some embodiments, storage device 160 may be integrated or included in one or more other components of the system (e.g., processing device 120, target command center 110, or other possible components).

The AR glasses 130 are intelligent wearable devices with functions of photographing, communication, and the like. The AR glasses 130 may capture an image of an object in the area through the camera to obtain related data and/or information of the object. In some embodiments, one or more cameras may be included on AR glasses 130. For example, the AR glasses may include at least one of a wide angle camera, a fisheye camera, a monocular camera, a multi-eye camera (binocular camera), a depth camera (RGBD camera), a dome camera, an infrared camera, a Digital Video Recorder (DVR), etc., or any combination thereof. In some embodiments, the AR glasses may acquire electrolysis data for the field inspection. In some embodiments, the AR glasses may also direct the field producer to operate based on the received control instructions.

The automated control system 140 may automatically control the operation of the on-site production facility according to a program. In some embodiments, the automated control system 140 may be a distributed control system (Distributed Control System, DCS) that may include an instruction dispatch processor and a plurality of logic programmable controllers (Program Logic Controller, PLC) located at the electrolysis process site. Each logic programmable controller may control one or more production devices to operate.

Network 150 may connect components of the system and/or connect the system with external resource components. Network 150 enables communication between the various components and with other components outside the system to facilitate the exchange of data and/or information. For example, the target command center 110 may exchange electrolytic data for field inspection with the AR glasses 130 via the network 150. For another example, the target command center 110 may also exchange equipment production data with an automation center via the network 150. In some embodiments, network 150 may be any one or more of a wired network or a wireless network. For example, the network 150 may include a cable network, a fiber optic network, a telecommunications network, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network, a Near Field Communication (NFC), an intra-device bus, an intra-device line, a cable connection, and the like, or any combination thereof. The network connection between the parts can be in one of the above-mentioned ways or in a plurality of ways. In some embodiments, the network may be a point-to-point, shared, centralized, etc. variety of topologies or a combination of topologies. In some embodiments, network 150 may include one or more network access points. For example, the network 150 may include wired or wireless network access points, such as base stations and/or network switching points 150-1, 150-2, …, through which one or more components of the electrolysis control system may be connected to the network 150 to exchange data and/or information.

FIG. 2 is a schematic diagram of a device of a remote coordinated electrolysis control system 200 according to some embodiments of the present disclosure. As shown in fig. 2, the electrolysis control system 200 may include a data acquisition unit 210, a data transmission unit 220, and a production control unit 230.

The data acquisition unit 210 may be configured to acquire electrolysis data. The electrolysis data comprises field inspection data and equipment production data corresponding to the field inspection data based on time. The field inspection data includes at least one of AR inspection data and automatic acquisition data. In some embodiments, the AR patrol data is acquired based on AR glasses shots worn by the field producer. In some embodiments, the automatic acquisition data is based on the automatic acquisition device performing a first operational acquisition of the production facility. In some embodiments, the data obtaining unit 210 is further configured to obtain the field inspection data based on the first trigger condition. The first trigger condition is determined based on at least one of a time interval and alarm information received from a production detection device.

The data transmission unit 220 may be configured to transmit the electrolysis data to a target command center, which is more than a threshold distance from the site. In some embodiments, the data transmission unit 220 is further configured to: and based on a second trigger condition, sending the electrolysis data to the target command center. In some embodiments, the second trigger condition is determined based on at least one of a time interval, alarm information received from a production detection device, and the electrolysis data.

The production control unit 230 may be configured to control the production process of the site based on the guidance opinions obtained from the target command center. In some embodiments, the production control unit 230 is further configured to: and sending a control instruction to at least one of an automatic control system and the AR glasses. In some embodiments, the control instructions are generated based on instructional opinions obtained from the target command center; the control instructions are for instructing the automated control system to perform a second operation and/or directing the on-site producer wearing the AR glasses to perform a third operation.

FIG. 3 is a schematic diagram of a remote coordinated electrolysis control system according to some embodiments of the present disclosure. As shown in fig. 3, the remote coordinated electrolysis control system 300 includes:

and a data acquisition unit 210 for acquiring electrolysis data.

The electrolysis data are relevant production data in the electrolysis process. In some embodiments, the electrolysis data may include field inspection data and equipment production data corresponding to the field inspection data based on time.

In some embodiments, the data acquisition unit 210 may include a first data acquisition unit for acquiring field inspection data.

The field inspection data is data obtained on the field of inspection and electrolysis process. In some embodiments, the field inspection data may include at least one of AR inspection data and auto-acquired data.

The AR inspection data are field inspection data acquired by cameras of the AR glasses. In some embodiments, the AR patrol data is acquired based on AR glasses shots worn by the field producer.

In some embodiments, the AR glasses may detect a current location of a site producer wearing the AR glasses based on a GPS carried by the AR glasses, and display a site live-action photographed in real time by a camera of the AR glasses and a virtual guide identifier corresponding to the site live-action to the site producer based on the location of the site producer wearing the AR glasses.

In some embodiments, the virtual guideline identification may include a guideline identification for a tour route in a live-action. For example, the virtual guideline identification may include a navigational arrow to the on-site producer's current location to a tour route to a particular production device. In some embodiments, the first data acquisition unit may plan the tour route and send it to the AR glasses, and the further AR glasses may display a guide identifier of the tour route. In some embodiments, the AR glasses may detect a current location of a field producer wearing the AR glasses through a GPS and send the current location to a first data acquisition unit, which plans a patrol route based on the current location of the field producer, a target location to which the field producer needs to travel, and real-time environmental data on the field.

In some embodiments, the real-time environmental data on site may determine the obstacles of the route, and further, may avoid the obstacles for planning while planning the tour route. The obstacle may be a work area or other route being patrolled where a safe distance needs to be maintained.

In some embodiments, the live real-time environmental data may include current image data captured in real-time by an AR-glasses-based camera, and/or production facility data acquired from an internet-of-things platform. The production equipment data acquired from the internet of things platform can determine the production equipment that is operating and determine whether the location of the production equipment can be an obstacle based on the type of production equipment. In some embodiments, the first data acquisition unit may process live real-time environmental data based on the obstacle determination model to determine the position of the obstacle. For example, the obstacle determination model may include an image environment data layer and an obstacle prediction layer. The input of the image environment data layer may include current image data, outputting image features related to the obstacle. In some embodiments, the image environment data layer may be a convolutional neural network model. The inputs to the obstacle prediction layer may include production equipment data and image features acquired from an internet of things platform, and the outputs may be locations of obstacles. In some embodiments, the obstacle prediction layer may be a fully connected layer. The obstacle determination model may be trained via first training data, the first training data being derived based on historical data. The first training data includes: sample image data, sample production equipment data, and the label of the first training data is the position of the obstacle.

In some embodiments, the virtual guideline identification may include specifications that direct the operation of a particular field production device. For example, the virtual guideline identification may include an operation step of adding electrolyte to a specific electrolytic cell and an indication arrow in each operation step to an operation object.

In some embodiments, the virtual guideline identification may include an identification for alerting the on-site producer. For example, the virtual guideline identification may include a red alert, the "not wearing gloves-! ".

In some embodiments, the virtual guideline identification may be preset. For example, specifications for operating on-site production equipment are set in advance based on an operation manual. In some embodiments, the virtual guideline identification may be generated in real-time. For example, based on the generated tour route, a corresponding navigation arrow is generated in real time.

In some embodiments, the site producer wearing the AR glasses performs the inspection and inspection operation on the site according to the guide identifier, and at the same time, the camera of the AR glasses may take a photograph and/or video of the inspection and inspection operation of the site producer, thereby obtaining the AR inspection data.

Taking the example of acquiring AR inspection data, namely 'checking the image data of the cathode plate 2 of the electrolytic tank A', the AR glasses can detect the current position of the on-site producer A wearing the AR glasses through a GPS, and then display the on-site live view of the current position of the A, which is shot in real time by a camera of the AR glasses, and a navigation arrow from the current position of the A to the inspection route of the electrolytic tank A to the A based on a preset guide mark of the inspection route; when the AR glasses detect that the armor is positioned in the electrolytic tank A, displaying the electrolytic tank A shot by a camera of the AR glasses to the armor in real time, and acquiring the operation specification of the image data of the cathode plate 1 of the electrolytic tank A, wherein the operation specification comprises the first step of wearing gloves firstly, and meanwhile, the AR glasses can detect whether the armor is wearing the gloves or not through the camera, otherwise, continuously displaying warning words of wearing no gloves to the armor; further, the AR glasses may display the second step of the operating specification "hold arrow pointing position," slowly lifting "and virtual arrow on cathode plate 1 to the nail; … A completes the operation according to the virtual indication mark, and the AR glasses can shoot the patrol route of the A and the video of the inspection operation, so that AR patrol data are obtained.

The automatic acquisition data is the field inspection data acquired by the automatic acquisition device. In some embodiments, the automatically acquiring data is based on the automatically acquiring device performing a first operational acquisition of the production facility.

The automatic acquisition device is a device that automatically collects production data of the production facility.

In some embodiments, the automatic acquisition device may include a patrol robot that collects production equipment and/or product image data based on a preset patrol route. Accordingly, the first operation performed by the inspection robot on the production equipment may include a target object acquisition operation and a photographing operation. The target object may be a production device and/or a product. For example, the inspection robot is positioned to the electrolytic cell B based on a preset inspection route, then takes out the cathode plate 1 from the electrolytic cell B, and automatically acquires image data (such as an image of the cathode plate) through a camera mounted thereon.

In some embodiments, the automatic acquisition device may further include a patrol sensor that collects production facility detection data based on a preset patrol route. Accordingly, a first operation performed by the inspection sensor on the production equipment may include acquiring inspection data by the sensor. For example, the inspection sensor is positioned to the electrolyte temperature detection device of the electrolytic tank C based on a preset inspection route, and the current temperature parameter detected by the electrolyte temperature detection device is obtained by the mounted sensor.

In some embodiments, the AR glasses and the automatic acquisition device may also acquire electrolysis data in linkage.

For example, the data acquisition unit 210 may first detect whether the automatically acquired data meets the quality requirement and/or the quantity requirement, if so, take the automatically acquired data as the electrolysis data, otherwise send an instruction to the AR glasses to acquire the AR patrol data, and take the AR patrol data as the electrolysis data. For example, when the data acquisition unit 210 detects that the resolution of the image of the cathode plate 1 of the electrolytic cell a acquired by the inspection robot is insufficient, an instruction for acquiring the image of the cathode plate 1 of the electrolytic cell a is sent to the AR glasses, the site worker wearing the AR glasses acquires the image of the cathode plate 1 of the electrolytic cell a according to the inspection route and the operation specification displayed by the AR glasses based on the instruction, and the data acquisition unit 210 receives the image of the cathode plate 1 of the electrolytic cell a from the AR glasses as electrolysis data.

The first trigger condition is a condition for triggering acquisition of the field inspection data. In some embodiments, the data acquisition unit 210 may also acquire the field inspection data based on the first trigger condition. In some embodiments, the first trigger conditions for different field inspection data may be the same or different.

In some embodiments, the first trigger condition may be determined based on at least one of a time interval and alarm information received from the production detection device.

In some embodiments, the first trigger condition may be determined based on a time interval. The time interval may be a preset parameter, for example. For example, if the preset time interval is 3 hours, the data acquisition unit 210 acquires the field inspection data of all the production apparatuses currently based on the first trigger condition that "the current time interval is 3 hours from the last acquisition of the field inspection data". Still another example, the time interval may be automatically determined based on an inspection period of the production facility, a production period of the product, and the like. For example, if it is necessary to check whether the electrolyte temperature of the electrolytic cell D is normal every 4 hours, the data acquisition unit 210 acquires the electrolyte temperature of the current electrolytic cell D based on the first trigger condition "the current time interval of 4 hours from the last acquisition of the electrolyte temperature of the electrolytic cell D"; the production cycle of the metal plate is 5 days, and the data acquisition unit 210 acquires the image data of the current cathode plate based on the first trigger condition that the current time is 24 hours apart from the last acquisition of the image data of the cathode plate.

In some embodiments, the first trigger condition may be determined based on alarm information received from the production detection device. The production detection device is a device for detecting and alarming production data. In some embodiments, the production detection device may include, but is not limited to, a temperature detection device, a short circuit real-time detection device, a circulation pump operation detection device, a sheet metal quality detection device, and the like. When the production detection device detects that the production data is abnormal, alarm information may be transmitted to the data acquisition unit 210. For example, when the temperature detection device of the electrolytic cell D detects that the electrolyte temperature of the electrolytic cell D exceeds the threshold value, the electrolyte temperature abnormality warning information of the electrolytic cell D is sent to the data acquisition unit 210. For another example, when the short circuit real-time detection device of the electrolytic bath E detects that the circuit of the electrolytic bath E is short-circuited, the circuit abnormality warning information of the electrolytic bath E is sent to the data acquisition unit 210.

In some embodiments, the data acquisition unit 210 may instruct the on-site producer to wear AR glasses to acquire AR patrol data based on the virtual indication identifier based on the alarm information, or instruct the automatic acquisition device to acquire the automatic acquisition data. Continuing with the above example, the data acquisition unit 210 may instruct the on-site producer to wear AR glasses to acquire the current image of the electrolytic cell D based on the virtual indication mark, or instruct the patrol sensor to acquire the current electrolyte temperature, or the like, based on the electrolyte temperature abnormality alarm information of the electrolytic cell D.

In some embodiments, the data acquisition unit 210 may also acquire field inspection data based on the request of the expert group. For a detailed description of the acquisition of the field inspection data based on the request of the expert group, reference may be made to the data transmission unit 220, which will not be described herein.

In some embodiments, the data acquisition unit 210 may include a second data acquisition unit for acquiring device production data.

The plant production data is data automatically generated during operation of the production plant of the electrolysis process. For example, temperature data during electrolysis in the electrolytic tank, flow data during operation of the circulation pump, etc.

In some embodiments, the device production data originates from an internet of things data platform connected to the system. The internet of things (The Internet of Things, IOT) is an operating mechanism that shares information and generates useful information between items over a connection network. Wherein the article may be a production facility of an electrolytic process. The IOT device is a device that collects production device information in the internet of things. In some embodiments, the IOT device may be the production device itself. For example, the IOT device may be an automatic addition device that collects the additive dose. In some embodiments, IOT devices may also be different from production devices. For example, the production facility may be an electrolyzer and the IOT facility may be a temperature sensor that collects electrolyzer temperature information. For another example, the production facility may be a circulation pump and the IOT facility may be a sensor that collects circulation pump flow. The production equipment is accessed to the network by the Internet of things through various IOT equipment, so that the storage and management of the equipment production data are realized through an Internet of things data platform.

In some embodiments, the data obtaining unit 210 may determine the obtaining time point T of the on-site inspection data, and then obtain the device production data corresponding to the time point T from the internet platform, that is, the data generated by the production device at the time point T. Continuing the above example, the data acquisition unit 210 based on the first trigger condition "electrolyte temperature abnormality warning information of the electrolytic cell D", the on-site inspection data of 7.7.7.8 points at the time point 2021 were obtained "the electrolyte of the electrolytic tank D was 2021 the temperature of 8 o 'clock at 7.7.year at 40 ℃" and "image of 8 o' clock at 7.year of 2021" for electrolyzer D. Further, the data acquisition unit 210 may acquire production equipment data corresponding to the time point 2021, 7 months, 7 days, 8 integers from the internet platform: "circulation pump flow rate of 7 th day 8 of 2021 for electrolytic tank D", "circulation pump power of 8 th day 7 of 2021 for electrolytic tank D", "site temperature of 8 th day 7 of 2021 for 7 th day 7 of 2021", "power of 8 th day 7 of 2021 for heat exchanger H of electrolytic tank D") "additive dose for type I electrolyte of cell D at 8 points 7/2021", "additive dose for type II electrolyte of cell D at 8/7/2021", etc.

In some embodiments, the electrolysis data may also include raw material data. Raw material data is data relating to raw materials used in electrolytic processes. In some embodiments, the raw material data may include plate raw material data and electrolyte raw material data. The plate raw material data may include plate composition (e.g., copper, lithium), plate weight (500 g), plate size (200 cm. Times.200 cm. Times.5 cm), plate number (e.g., 001, 002), plate position (e.g., position 1 of cell D), etc. Electrolyte feed data may include electrolyte composition (e.g., 60% hydrochloric acid solution), electrolyte volume (1000 mL), and electrolyte location (cell D), among others.

Raw material data is data determined based on an electrolytic process design prior to production run. In some embodiments, raw material data may be pre-stored in the internet of things platform, and the data acquisition unit 210 may acquire raw material data from the internet of things platform through AR glasses and/or an automatic acquisition device. For example, the storage position of the raw material data in the internet of things can be set (such as pasting, etching, laser printing and the like) on the raw material in the form of a website, a two-dimensional code or a bar code; further, the site producer can identify the website, the two-dimensional code or the bar code through the camera on the AR glasses, so that the storage position of raw material data in the logistics network is accessed, the raw material data is obtained, and similarly, the patrol robot can also obtain the raw material data through the carried camera.

In some embodiments, the data acquisition unit 210 may acquire raw material data based on the guidance opinion of the expert. The related description of acquiring raw material data based on the guidance opinions of the specialists may be referred to the production control unit 230, and will not be repeated here.

And the data transmission unit 220 is used for sending the electrolysis data to a target command center.

The target command center is a platform for remotely guiding the electrolysis process and comprises an expert group and one or more terminal devices used by the expert group. The expert group is composed of advanced technicians, researchers, etc. in various fields related to the electrolytic process.

In some embodiments, the expert group may include an initial expert group and an updated expert group.

The initial expert group is the first expert group to determine. The initial expert group is used for solving the abnormal condition of the electrolytic process corresponding to at least one initial problem type. See further below for more on the type of problem.

The at least one initial question type is a question type that is initially determined based on electrolysis data. In some embodiments, at least one initial question type may be determined by a first model based on the electrolysis data.

In some embodiments, the first model may be a classification model. Specifically, the first model may map the input electrolytic data into a plurality of values or probabilities, each value or probability corresponding to a candidate initial question type, and obtain at least one initial question type based on the plurality of values or probabilities. For example, a candidate initial question type corresponding to a value or probability greater than a threshold (e.g., 0.6) is taken as the initial question type. For another example, the candidate initial question type corresponding to the first N values or probabilities is taken as the initial question type.

In some embodiments, the first model may be, but is not limited to, a support vector machine model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a convolutional neural network (Convolutional Neural Network, CNN) model, a recurrent neural network (Recurrent Neural Network, RNN) model, a long short term memory network (Long Short Term Memory Network, LSTM) model, and the like.

Illustratively, the first model maps the input electrolysis data "electrolyte temperature 40 ℃ for cell D" and "image for cell D" to a plurality of probabilities corresponding to short circuit problem, circulation pump problem, electrolyte composition problem, electrolyte temperature problem …, respectively: 0.3, 0.5, 0.7, …, then regarding the electrolyte temperature problem corresponding to a probability 0.7 greater than a threshold value of 0.6 as at least one initial problem type.

In some embodiments, the first model may be trained based on the second training sample. The first training sample may include historical electrolysis data. The second training label may be a question type corresponding to manually noted historical electrolysis data.

In some embodiments, the data transmission unit 220 may match determine an initial expert group from expert information of the expert database based on at least one initial question type.

In some embodiments, the data transmission unit 220 may first determine at least one domain to which the expert group relates based on at least one initial question type. Further, the data transmission unit 220 may match at least one expert from the expert information of the expert database through the search engine based on at least one field referred to by the expert group. The expert information at least comprises the expert field of the expert, the grade of the expert, the expert profile and the expert contact mode. For example, the data transmission unit 220 may determine that the expert group relates to the "electrolyte composition field" based on at least one initial problem type "electrolyte temperature problem", and obtain the experts of the expert field including the "electrolyte composition field" from the expert database.

In some embodiments, the Search engine may include, but is not limited to, one of an Elastic Search engine, a Sphinx engine, and an Xapian engine.

In some embodiments, the data transmission unit 220 may acquire a specific number of experts from at least one expert acquired by the matching based on a specific number of preset and/or manual inputs, and form an expert group. In some implementations, the data transmission unit 220 may acquire a specific number of experts at random, or may further acquire a specific number of experts through a ranking model based on the electrolysis data. In some embodiments, the ranking model may include, but is not limited to, a Text Rank model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a KNN classification model, a neural network model, and the like. The ranking model may be obtained through training of a third training sample. In some embodiments, the third training sample may include a plurality of experts and historical electrolysis data, and the label of the third training sample may be a sequence corresponding to each of the experts that are manually labeled.

Some embodiments of the present disclosure match members of an initial expert group based on an initial problem type determined from electrolysis data, so that the determined initial expert group may be more targeted to abnormal conditions of the electrolysis process, thereby improving efficiency of a remote system and avoiding waste of expert resources.

The updated expert group is an expert group of the replaced expert member, and can be an expert group updated based on the initial expert group or an expert group updated based on the last updated expert group. The updating expert group is used for solving abnormal conditions of the electrolytic process corresponding to at least one updating problem type.

The update issue type is an issue type determined based on electrolytic data further acquired by interaction with an expert group (initial expert group or update expert group determined last time).

In some embodiments, the at least one updated issue type may be an issue type outside of the scope of the at least one last determined issue type. For example, the last determined question type is an initial question type, at least one initial question type includes only "electrolyte temperature questions", and at least one updated question type may include at least one of "electrolyte composition questions", "short circuit questions", and the like. For another example, the last determined problem type is a renewal problem type, including "electrolyte composition problem" and "short circuit problem", and the at least one renewal problem type may include "circulation pump problem".

In some embodiments, the at least one updated issue type may be a specific sub-issue for which the at least one last determined issue type corresponds. For example, the last determined problem type is an initial problem type, at least one initial problem type includes an "electrolyte temperature problem", and at least one updated problem type may include an "electrolyte temperature problem caused by a heat exchanger failure", or the like. For another example, the last determined problem type is a retrofit problem type, including "electrolyte temperature problem due to heat exchanger failure", and at least one retrofit problem type may include "electrolyte temperature problem due to heat exchanger fouling".

In some embodiments, the update issue type may be determined based on expert group opinion. The detailed description of the update issue type may be referred to in fig. 4 and the related description thereof, and will not be repeated here.

It will be appreciated that an expert group that is determined based on at least one last determined problem type match may not be able to address an electrolytic process anomaly corresponding to at least one current updated problem type, and thus, an updated expert group needs to be redetermined based on at least one current updated problem type. For example, an initial expert group "related to the electrolyte temperature field" that is matched based on at least one initial problem type "electrolyte temperature problem" cannot solve the update problem type "electrolyte composition problem", and thus an update expert group, i.e., an expert group related to the "electrolyte composition field" is determined, is required.

In some embodiments, the data transmission unit 220 may match the updated expert group from the expert information in the expert database based on at least one updated problem type and the difficulty level.

The difficulty level of each of the at least one update issue may characterize a level of domain expert corresponding to the update issue. It will be appreciated that the more difficult it is to update the problem, the higher the level of the corresponding domain expert needs. For example, at least one update problem, namely "electrolyte temperature problem due to abnormal flow of the circulation pump", is relatively simple, and the corresponding level of experts in the field of circulation pumps only requires a primary expert. As another example, at least one update problem, "electrolyte temperature problem due to heat exchanger failure," is more difficult, and the corresponding level of heat exchanger domain expertise requires a high level of expertise.

In some embodiments, the difficulty level of at least one update issue type may be represented by a difficulty coefficient. For example, a number between 0 and 1, the larger the number, the more difficult it is to update the problem type. In some embodiments, the difficulty level may also be used to represent the difficulty level of at least one update issue type. For example, the higher the level, the more difficult it is to indicate the type of update problem.

In some embodiments, an expert group (initial expert group or last determined updated expert group) may request to re-acquire electrolysis data to further determine the ease of at least one updated issue type based on re-acquiring electrolysis data. For example, the expert group may send a data acquisition request to the data acquisition unit 210, the data acquisition request including an electrolysis data type, and the data acquisition unit 210 may acquire corresponding electrolysis data based on the electrolysis data type and send to the expert group.

In some embodiments, the data transmission unit 220 may determine the difficulty level of the at least one update issue type based on the re-acquired field inspection data, the equipment production data, and the at least one update issue type via the second model. The second model may include a first judgment layer, a second judgment layer, and a coefficient output layer.

The input to the first determination layer may include field inspection data and at least one updated problem type, and the output may be at least one first difficulty factor. The first difficulty coefficient may reflect a difficulty level of the at least one updated issue type based on the field inspection data. For example 0.8. For example, the first decision layer may fuse the field inspection data and the at least one updated issue type into at least one first vector, and then map the at least one first vector to at least one first difficulty coefficient.

The input to the first decision layer may include equipment production data and at least one updated problem type, and the output may be at least one second difficulty factor. The at least one second difficulty factor may reflect a difficulty level of the at least one update issue type based on the device production data. For example 0.5. For example, the second decision layer may fuse the device production data and the at least one update issue type into at least one second vector, which is then mapped to at least one second difficulty coefficient.

The input of the coefficient output layer may include at least one first difficulty coefficient, at least one second difficulty coefficient, and the output may be at least one difficulty coefficient of the update problem type. For example, the coefficient output layer may perform weighted summation on the first difficulty coefficient and the second difficulty coefficient corresponding to each update problem type, to obtain the corresponding difficulty coefficient. The first weight corresponding to the first difficulty coefficient may be determined based on a euclidean distance between a vector of the on-site inspection data and a vector of the corresponding update problem type, and the second weight corresponding to the second difficulty coefficient may be determined based on a euclidean distance between a vector of the equipment production data and a vector of the corresponding update problem type.

In some embodiments, the second model may include, but is not limited to, a convolutional neural network model, a recurrent neural network model, a long-term memory network model, and the like.

Illustratively, the data transmission unit 220 may acquire the corresponding difficulty level of 0.8 through the second model based on the re-acquired field inspection data "electrolyte temperature 40 ℃ of the electrolytic tank D", "image of the electrolytic tank D", the equipment production data equipment production parameters "heat exchanger electrolyte input temperature 38 ℃ and" heat exchanger electrolyte output temperature 40 ℃ corresponding to the time point of re-acquiring the field inspection data ", and the at least one update problem type" electrolyte temperature problem caused by heat exchanger failure ".

In some embodiments, the second model may be trained based on a fourth training sample. The fourth training sample may include sample field inspection data, sample equipment production data, and sample problem types, and the label of the fourth training sample may be a difficulty level of the sample problem types. The fourth training sample may be obtained based on historical data.

Some embodiments of the present disclosure combine on-site electrolysis data to determine the difficulty level of updating the problem type, so that on one hand, the determined difficulty level is not separated from the on-site electrolysis process, and thus the difficulty level of updating the problem type is more real-time; on the other hand, the first judgment layer and the second judgment layer of the second model respectively determine a first difficulty coefficient and a second difficulty coefficient based on field inspection data and equipment production data, and the difficulty degree of the update problem can be reflected from different data dimensions; in addition, the weights of the first difficulty coefficient and the second difficulty coefficient are determined based on Euclidean distances between the vector of the field inspection data and the vector of the equipment production data and the vector corresponding to the update problem type, and the difficulty level can be determined by combining the influence of the data with different dimensions on the update problem, so that the accuracy of the difficulty level is improved.

In some embodiments, the data transmission unit 220 may determine at least one update field to which the update expert group relates based on at least one update issue type, and determine a level of the expert in each update field based on a difficulty level of the at least one update issue type. For example, based on at least one update issue type "electrolyte temperature issue caused by heat exchanger failure" determining that an expert group relates to the heat exchanger field, based on the difficulty level of the issue of 0.8, the expert level of the heat exchanger field in the update expert group can be determined to be advanced.

In some embodiments, the production control unit 230 may determine the updated expert group by matching at least one expert from the expert information of the expert database through the search engine based on at least one domain and a level of each domain expert to which the updated expert group relates.

According to some embodiments of the present disclosure, at least one update problem may be determined according to electrolysis data further acquired by the expert group, and the expert group may be redetermined based on at least one update problem type (i.e., update expert group), so that bidirectional interaction between the electrolysis process field and the target command center is realized, so that the expert group of the target command center may be adjusted according to the field, and meanwhile, different electrolysis data may be provided on the field based on the requirements of the target command center, thereby improving flexibility and effectiveness of remote collaboration.

In some embodiments, the system 300 further comprises a reference data acquisition unit, which may be used to acquire reference data.

It is understood that the electrolysis data acquired by the data acquisition unit 210 may contain a large amount of data unrelated to the abnormality of the electrolysis process. In some embodiments, the data transmission unit 220 may transmit only a portion of the electrolysis data related to the electrolysis process anomaly to the target command center. The reference data is electrolysis data relating to an abnormality in the electrolysis process.

In some embodiments, the reference data acquisition unit may determine the reference data corresponding to the at least one question type based on the at least one question type.

At least one problem type refers to a problem type in which an abnormality occurs in the electrolytic process. For example, the problem types may include, but are not limited to, short circuit problems, circulation pump problems, electrolyte composition problems, electrolyte temperature problems, and the like.

In some embodiments, the at least one question type comprises at least one initial question type. As previously described, at least one initial question type may be determined by a first model based on the electrolysis data.

In some embodiments, the at least one question type further comprises at least one updated question type. As previously described, the at least one updated issue type may be an issue type outside of the scope of the at least one last determined issue type, or may be a specific sub-issue corresponding to the at least one last determined issue type. In some embodiments, at least one updated question type may be obtained based on the expert group's reference opinion and at least one question type. A detailed description of the obtaining of the at least one update issue type may be found in fig. 4, and will not be repeated here.

In some embodiments, the reference data acquisition unit may acquire the reference data based on a data screening model. The input of the data screening model comprises at least one question type and electrolysis data, and the output is reference data.

For example, the data screening model may first obtain a data vector for each piece of electrolysis data; acquiring Attention vectors between at least one problem type and a plurality of data vectors based on an Attention mechanism; then, based on the attention vector, acquiring a corresponding association degree of each piece of electrolysis data, wherein the association degree characterizes the association degree of the electrolysis data and at least one problem type; further, electrolytic data corresponding to the degree of association greater than the threshold of degree of association is output as reference data.

The reference data acquisition unit acquires the reference data "circulation pump flow of the electrolytic cell D", "on-site temperature 34 ℃ and" current of the electrolytic cell D "from a large amount of electrolytic data based on at least one initial problem type" electrolyte temperature problem ". Still another exemplary embodiment of the present invention provides a method for determining a temperature of electrolyte due to a failure of a heat exchanger based on at least one updated problem type, wherein the reference data acquisition unit may acquire reference data of "a heat exchanger electrolyte input temperature of 38 ℃ and" a heat exchanger electrolyte output temperature of 40 ℃ from a large amount of electrolysis data.

In some embodiments, the data screening model may be trained based on the fifth training sample. The fifth training sample may include sample electrolysis data and sample question types. The label of the fifth training data may be a correlation of each of the manually labeled sample electrolysis data with the sample question type.

In some embodiments, after the reference data acquisition unit acquires the corresponding reference data based on the initial question type, the data transmission unit 220 may send the reference data to the initial expert group in the target conductor. In some embodiments, after the reference data acquiring unit acquires the corresponding electrolysis data based on the update issue type, the data transmitting unit 220 may send the reference data to the update expert group in the target conductor.

In some embodiments of the present disclosure, the problem type is determined based on the electrolysis data, and the reference data related to the problem is screened from the mass production equipment data according to the problem type, so that effective information can be quickly provided for the expert group, thereby improving the efficiency and effectiveness of remote collaboration.

In some embodiments, the data transmission unit 220 may send the electrolysis data or the reference data to the target command center based on the second trigger condition.

The second triggering condition refers to a condition for triggering the sending of electrolytic data to the target command center. In some embodiments, the second trigger condition is determined based on at least one of a time interval, alarm information received from the production detection device, and the electrolysis data.

Similarly to the first trigger condition, the time interval corresponding to the second trigger condition may be a preset parameter, and may also be automatically determined based on an inspection period of the production apparatus, a production period of the product, or the like. For example, if the production facility cell D needs to check whether its electrolyte temperature is normal every 4 hours, the data transmission unit 220 transmits the current electrolyte temperature of the cell D to the target command center based on the second trigger condition "the current time is 4 hours from the last time the electrolyte temperature of the cell D was transmitted".

In some embodiments, the time interval corresponding to the second trigger condition may be dynamically varied based on the production process parameters and raw material data. In some embodiments, a predicted electrolysis rate is obtained based on the historical electrolysis rate of the electrode plate, and then a time interval is determined based on the predicted electrolysis rate and the AR historical patrol frequency.

The AR historical inspection frequency refers to the number of times that on-site production personnel wear AR glasses to acquire AR inspection data in a historical unit time, such as 1 hour and 5 times. In some embodiments, the AR historical patrol frequency may be obtained from AR glasses. It will be appreciated that the inspection frequency of the AR glasses may be changed due to a change in the production rate of the product, for example, if the production rate of the product is increased, the inspection frequency of the AR glasses is correspondingly increased, and the time interval for transmitting the electrolysis data is correspondingly shortened. Wherein the production rate of the metal plate can be characterized by the electrolysis rate of the electrode plate.

For example, the predicted electrolysis rate may be obtained based on historical electrolysis rates corresponding to a plurality of (e.g., 5) historical time points. Illustratively, a fitting function of historical electrolysis rates corresponding to a plurality of historical time points is obtained, thereby obtaining a predicted electrolysis rate for the predicted time point. Further, the AR predicted patrol frequency may be obtained based on the rate of increase of the predicted electrolysis rate and the AR historical patrol frequency, and the time interval may be determined based on the AR predicted training frequency. For example, if the predicted rate of increase of the electrolysis rate is 20% compared to the average historical electrolysis rate of the electrolysis plate, the AR predicted patrol frequency may be obtained to be 5× (1+20%) =6 times/hour based on the AR historical patrol frequency, and the time interval is further determined to be 10 minutes.

In some embodiments, the second trigger condition may also be determined based on alarm information received from the production detection device. The related description of the alarm information may refer to the data acquisition unit 210 and the related description thereof, and will not be repeated herein. For example, the data transmission unit 220 transmits electrolysis data to the target command center based on the second trigger condition "electrolyte temperature abnormality warning information of the electrolytic tank D".

In some embodiments, the data transmission unit 220 sends the electrolysis data to the target command center through the network after determining that the second trigger condition is satisfied. For example, the field inspection data "electrolyte temperature 40 ℃ of the electrolytic tank D" and "image of the electrolytic tank D" and the equipment production parameters "circulation pump flow", "field temperature 34 ℃ and" electrolytic tank current "are transmitted to the target command center.

In some embodiments, the data transmission unit 220 further includes a transmission judgment unit. The transmission judgment unit may judge whether to transmit the electrolysis data or the reference data to the target command center based on the on-site inspection data and the equipment production data, and in response, the data transmission unit 220 may transmit the electrolysis data or the reference data.

In some embodiments, the data transmission unit 220 may determine whether the acquired electrolysis data or reference data is abnormal, and then determine whether to transmit the electrolysis data or reference data to the target command center in conjunction with the simulation system.

In some embodiments, the data transmission unit 220 may determine whether the acquired electrolysis data or reference data is abnormal based on a plurality of historical electrolysis data or reference data. For example, the data transmission unit may determine whether the acquired electrolysis data (e.g., the current electrolysis rate, the current electrode plate image data, and the current temperature) is abnormal, such as the acquired electrolysis data and the historical electrolysis data do not match, based on the historical electrolysis data (e.g., the historical electrolysis rate, the historical electrode plate image data, the historical temperature, and the like) corresponding to a plurality of (e.g., 10) historical time points.

In some embodiments, the data transmission unit 220 may determine whether the acquired electrolysis data or reference data is abnormal based on the third model. The third model may include an image data matching layer, a parameter data matching layer, and a judgment layer.

The input of the image data matching layer comprises historical electrode plate image data and current electrode plate image data corresponding to a plurality of historical time points, and the output comprises historical image features and current historical image features corresponding to the plurality of historical time points. In some embodiments, the image data matching layer may be a convolutional neural network model.

The input of the parameter data matching layer comprises a plurality of historical electrolysis rates and current electrolysis rates corresponding to historical time points, and historical temperatures and current temperatures corresponding to the historical time points, and a first matching result comprising the historical electrolysis rates and the current electrolysis rates corresponding to the historical time points and a second matching result comprising the historical temperatures and the current temperatures corresponding to the historical time points are output. Wherein the first and second matching results may include "match" and "no match". In some embodiments, the image data matching layer may be a deep neural network model.

The input of the judgment layer may include the historical image features and the current historical image features corresponding to the plurality of historical time points, the first matching result and the second matching result, and the output may be the judgment result. Specifically, the judgment can merge the historical image features corresponding to the plurality of historical time points and the current historical image features, the first matching result and the second matching result into a judgment vector, map the judgment vector into a numerical value, and output a judgment result of yes when the numerical value is larger than a threshold value, namely judge that the acquired electrolytic data or the reference data is abnormal; otherwise, outputting a judging result of no, namely judging that the acquired electrolysis data or reference data is not abnormal. In some embodiments, the decision layer may be a recurrent neural network model.

The judging layer acquires a judging result based on the matching results of the image data features and the parameter data corresponding to the plurality of historical time points, and can judge whether the electrolytic data or the reference data is abnormal based on the features and the results at the same time, so that the accuracy of the judging result is improved.

In some embodiments, the third model may be trained based on the sixth training sample. The sixth training sample may include a positive sample and a negative sample. The positive samples may include historical electrolysis rates, historical electrode plate image data, and historical temperatures corresponding to a plurality of historical time points, and actual electrolysis rates, actual electrode plate image data, and actual temperatures corresponding to actual time points. The actual time point is a certain time point after a plurality of history time points. The label of the positive sample is "yes". The negative sample may include historical electrolysis rates, historical electrode plate image data, and historical temperatures corresponding to the plurality of historical time points, as well as artificially noted abnormal electrolysis rates, abnormal electrode plate image data, and abnormal temperatures. The label of the negative sample is no.

In some embodiments, the third model may be obtained by co-training with the data screening model. In some embodiments, the initial third model and the initial data screening model may be trained based on a number of labeled seventh training samples. Specifically, a seventh training sample with a label is input into an initial data screening model, parameters of the initial data screening model and parameters of the initial third model are updated through training until the trained intermediate data screening model and intermediate third model meet preset conditions, and the trained data screening model and the trained third model are obtained, wherein the preset conditions can be that a loss function is smaller than a threshold value, convergence is achieved, or a training period reaches the threshold value. In some embodiments, the seventh training sample may include a positive sample and a negative sample. The positive sample may include historical electrolysis data, at least one historical problem type, an actual electrolysis rate corresponding to an actual point in time, actual electrode plate image data, and an actual temperature. The label of the positive sample is "yes". The negative samples may include historical electrolysis data, at least one historical problem type, artificially noted abnormal electrolysis rates, abnormal electrode plate image data, and abnormal temperatures. The label of the negative sample is no.

In some embodiments, the data transmission unit 220 may further determine whether the retrieved electrolytic data or the reference data is abnormal based on a preset threshold range. Illustratively, when the retrieved electrolysis data or reference data is within a preset threshold range, it is determined that the retrieved electrolysis data or reference data is not abnormal, otherwise it is determined that the retrieved electrolysis data or reference data is abnormal.

In some embodiments, if the electrolysis data or the reference data is not abnormal, remote assistance is not needed, if the obtained electrolysis data or the reference data is abnormal, further judging whether a corresponding control scheme exists through the simulation system, if so, judging that remote assistance is not needed, otherwise, judging that remote assistance is needed. The simulation system may retrieve a corresponding control scheme or remote assistance request based on the entered abnormal electrolysis data or reference data.

In some embodiments, the simulation system may include a retrieval database. The search term may include historical electrolysis data or reference data, and the search value may be historical expert guidance opinion corresponding to the historical electrolysis data or reference data.

In some embodiments, the simulation system may further include a solution determination model. The protocol determination model may automatically generate expert guidance opinions based on the electrolysis data or the reference data. In some embodiments, the regimen determination model may be based on an eighth training sample acquisition. In some embodiments, the eighth training sample may include historical electrolysis data (or historical reference data). The eighth training label may be historical expert guidance opinion corresponding to historical electrolysis data or reference data.

Illustratively, the data transmission unit 220 determines that the electrolysis process does not have an abnormal condition according to the electrolysis data acquired based on the time interval, and/or determines whether the abnormal electrolysis data has a corresponding control scheme in the simulation system based on the electrolysis data acquired from the alarm information received from the production detection device, if so, the abnormal electrolysis data can be solved by an on-site producer and/or controlled by an automatic control system based on the control scheme without remote assistance, otherwise, remote assistance is required, and the second trigger condition is satisfied. The detailed description of the automatic control system may refer to the production control unit 230 and the description thereof, and will not be repeated herein.

In some embodiments, the data transmission unit 220 may also determine whether to transmit electrolytic data or reference data to the target command center based on the difficulty level of at least one question type (at least one initial question type or at least one updated question type).

In some embodiments, the data transmission unit 220 may predict the difficulty level of the initial question type based on the initial question type and its corresponding equipment production parameters through a fourth model. For example, if there are parameters that obviously correspond to the initial problem type in the corresponding equipment production parameters, the description is easier. Regarding the related description of predicting the difficulty level of the initial problem type based on the initial problem type and the corresponding equipment production parameters thereof through the fourth model, reference may be made to predicting the difficulty level of updating the problem type, which will not be described herein.

In some embodiments, it may be determined whether to send the electrolysis data or the reference data to the initial expert group or the update expert group based on the difficulty level of at least one of the initial question type or the update question type and the first preset condition.

In some embodiments, the first preset condition may include: when the difficulty level is greater than the first transmission threshold, the electrolysis data or the reference data are sent to an expert group; when the difficulty level is smaller than the first transmission threshold and larger than the second transmission threshold, acquiring a control scheme from the simulation system based on the electrolysis data or the reference data, and sending the control scheme and the electrolysis data or the reference data to an expert group; and when the difficulty level is smaller than the first transmission threshold value, directly transmitting the control scheme acquired in the simulation system based on the electrolysis data or the reference data to the expert group. The first transmission threshold and the second transmission threshold may be determined based on a problem type. For example, the first and second transmission thresholds may be determined to be 0.3 and 0.1, respectively, based on the update problem type "electrolyte temperature problem caused by heat exchanger failure". For another example, the first transmission threshold and the second transmission threshold may be determined to be 0.5 and 0.3, respectively, based on the update problem type being "electrolyte temperature problem caused by the circulation pump flow abnormality".

Illustratively, when the difficulty level of the at least one update problem "electrolyte temperature problem caused by heat exchanger failure" is 0.8, satisfying "greater than the first transmission threshold value of 0.3", the on-site inspection data "electrolyte temperature of the electrolytic tank D40 ℃," image of the electrolytic tank D "and the equipment production parameters" heat exchanger electrolyte input temperature 38 ℃ and "heat exchanger electrolyte output temperature 40 ℃) are transmitted to the target command center.

According to the method and the device for testing the abnormal condition control capacity of the electrolytic process of the simulation system, the participation degree of the target command center is determined based on the difficulty degree of the problem type, so that expert resources can be prevented from being wasted, the abnormal condition control capacity of the electrolytic process of the simulation system can be tested, more retrieval data and training data can be obtained for the simulation system, and the application range of the simulation system is improved.

In some embodiments, the data transmission unit 220 may transmit the electrolysis data or the reference data to an expert group of the target command center. The expert group may be an expert group determined based on the initial question type (also called initial expert group), or may be an updated expert group.

In some embodiments, the data transmission unit 220 may further determine the transmitted reference data required by each expert member based on the difficulty level of at least one question type and the expert members of the expert group. In some embodiments, the data transmission unit may determine the transmitted reference data required by each expert member based on the fifth model.

In some embodiments, the fifth model may determine a demand vector corresponding to the expert member based on the input difficulty level of the at least one question type and information of a certain expert member in the expert group, and then determine transmitted electrolysis data (or reference data) required by the corresponding expert member based on the demand vector corresponding to the expert member and the electrolysis data (or reference data).

In some embodiments, the fifth model may include a data type determination layer, a data range determination layer, and a data screening layer.

The input of the data type determination layer may include the professional domain of a member of the expert group, and the output may be the data requirement type corresponding to the member. For example, the data type determination layer may output a data requirement type "machine operation parameter" corresponding to a certain expert member based on the input of the expert domain "machine" of the expert member. In some embodiments, the data type determination layer may be a classification model, such as a support vector machine model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a KNN classification model, a neural network model, and the like.

The input of the data range determination layer may include an expert level of the expert member and a difficulty level of at least one question type, and the output may be a data range required by the expert member. In some embodiments, the data volume percentage may be used to represent the range of data that the expert member needs. It will be appreciated that the higher the expert level, the simpler the problem type, the smaller the data range and vice versa. The data range determining layer may first obtain the matching difficulty level corresponding to the expert level of the expert member, and then obtain the data volume percentage based on the matching difficulty level and the difficulty level of at least one problem type. The matching difficulty degree corresponding to the expert level can be determined based on a preset corresponding relation. For example, the data range determining layer may obtain the matching difficulty level of "0.4" based on the expert level "II" of the expert member a, and then obtain the data amount percentage of 0.8/(0.8-0.4) ×100% =200% based on the difficulty level of 0.8 of the at least one question type. In some embodiments, when the data volume percentage is less than 100%, the data volume percentage may be directly valued at 100%.

The input of the data screening layer comprises electrolysis data or reference data, the data requirement type corresponding to a certain expert member in the expert group, the data range required by the expert member, and the output of the data screening layer is the electrolysis data or reference data required by the expert member. The data screening layer may screen candidate electrolytic data (or candidate reference data) from electrolytic data or reference data based on the data requirement type corresponding to the expert member, further screen candidate electrolytic data (or candidate reference data) similar to the data requirement type from electrolytic data or reference data based on the data range required by the expert member, and finally use all candidate electrolytic data (or candidate reference data) as electrolytic data (or candidate reference data) required by the expert member. The candidate electrolysis data (or candidate reference data) similar to the data demand type can be the electrolysis data (or reference data) of similar equipment, or can be the electrolysis data (or reference data) of the same type.

For example, the data screening layer may screen candidate electrolysis data such as "circulation pump flow", "circulation pump power" and "circulation pump current" from the electrolysis data based on the data demand type "mechanical operation parameter" corresponding to expert member a, and further screen candidate electrolysis data such as "field temperature", "electrolyte temperature" and "cell current" similar to the "mechanical operation parameter" from the electrolysis data based on 200% of the data amount.

Similarly, the fifth model may also be based on the expert field circuit of expert member b, the expert grade, and the expert field thermal, expert grade of expert member c, to obtain the reference data that expert member b and expert member c need to transmit as "electrolyte temperature 40 ℃ of electrolyte tank D, image of electrolyte tank D", none and "electrolyte temperature 40 ℃ of electrolyte tank D, heat exchanger electrolyte input temperature 38 ℃, heat exchanger electrolyte output temperature 40 ℃", respectively.

In some embodiments, the fifth model may include, but is not limited to, a ELMo (Embedding from Language Models) model, a GPT (generated Pre-tracking) model, a BERT (Bidirectional Encoder Representation from Transformers) model, and the like.

Some embodiments of the present description enable reference data that each expert member needs to transmit to be matched with the type of problem (or area of expertise) that the expert member addresses by based on the difficulty level of at least one problem type and the expert members in the expert group; in addition, the data to be transmitted is further screened based on the difficulty level of the problem type and the expert level of the expert member (for example, the problem type is simpler, if the expert level is high, a small amount of reference data can be transmitted, if the expert level is low, more reference data can be transmitted), and the efficiency of data transmission can be improved while ensuring enough reference data for the expert member.

In some embodiments, the fifth model may be obtained based on historical data training. For example, a ninth training sample with a label is input into the initial fifth model, a loss function is constructed through the label and the prediction result of the initial fifth model, and parameters of the initial fifth model are updated based on the loss function in an iterative manner. And when the training initial fifth model meets the preset condition, the training is finished, and a trained fifth model is obtained. The preset conditions are that the loss function converges, the iteration times reach a threshold value, and the like.

In some embodiments, the ninth training sample may include historical expert member information, the difficulty level of the historical update issue, and historical electrolysis data. The tag includes a history expert member. The tag may be determined based on whether a history expert member issues a data acquisition request. For example, it is determined whether the tag includes each history expert member based on whether the history expert member issued a request for history electrolysis data in the training sample.

And a production control unit 230 for controlling the production process at the site based on the guidance opinions obtained from the target command center.

The instruction opinion is a countermeasure of the abnormal situation of the electrolytic process obtained by the target command center from the expert group (initial expert group or updated expert group).

In some embodiments, the target command center may determine the guide opinion based on reference opinion obtained from an expert group (e.g., an updated expert group or an initially updated expert group).

The reference opinion is an opinion of each expert member of the expert group. The experts in different fields can make corresponding reference comments for the field. In some embodiments, the expert members may determine the reference opinion in combination with reference data (i.e., electrolysis data related to an electrolysis process anomaly) obtained from the target command center.

Illustratively, expert members methyl the reference data "electrolyte temperature 40 ℃ for cell D, image" confirm reference opinion "for cell D circulating pump power is too low, resulting in insufficient electrolyte circulation volume, and thus too high temperature"; expert member B directly determines reference data which is irrelevant to circuit problems; the expert members propyl the reference data "electrolyte temperature 40 ℃ for cell D, heat exchanger electrolyte input temperature 38 ℃, heat exchanger electrolyte output temperature 40 ℃," determine reference opinion "that the heat exchanger failed resulting in the electrolyte not being cooled and thus being too hot".

In some embodiments, the target command center may provide a communication platform for a plurality of expert members of the expert group, any one expert may input reference comments to the target command center in the form of voice or text, and the rest of the experts may initiate a confirmation message for the reference comments input by the expert.

In some embodiments, the target guidance center may generate the guidance opinion based on the reference opinion of the plurality of experts after receiving the plurality of expert confirmation messages. In some embodiments, the instructional opinion may include a solution and may also include an electrolytic data acquisition request.

For example, the guidance opinion of the expert group may be a scheme of further acquiring specific electrolysis data in the form of voice "take an image of the inside by disassembling the heat exchanger H". For another example, the guidance opinion of the expert group may be "fouling inside heat exchanger H, overhauling heat exchanger H" in text. For another example, the guidance opinion of the expert group may also be "get condensate inlet and outlet temperature of heat exchanger H" in text form.

The control instructions are program instructions for controlling the electrolysis process. In some embodiments, the production control unit may generate the control instructions based on the instructional opinion. Specifically, the production control unit 230 may convert various forms (e.g., voice, video, etc.) of guide opinions into text form, extract key information from the text form of guide opinions through a text extraction algorithm, and compile the key information into control instructions. In some embodiments, the text extraction algorithm may include, but is not limited to, any one of or a combination of a TF/IDF algorithm, a Topic Model algorithm, a texttrank algorithm, a rake algorithm, or other algorithms.

For example, the production control unit 230 may convert the expert guidance opinion in the form of voice, namely "unpacking the heat exchanger H, photographing whether there is any scale in the interior" into the text form, extract the key information, namely "heat exchanger H, interior, photographing", and compile the control instructions corresponding to "unpacking the heat exchanger H" and "photographing the image of the interior of the heat exchanger H".

In some embodiments, control instructions are sent to at least one of an automated control system and the AR glasses.

Fig. 5 is an exemplary schematic diagram of a production control unit shown according to some embodiments of the present description. As shown in fig. 5, the production control unit 230 may also transmit control instructions to the automatic control system 140 and the AR glasses through a network.

In some embodiments, the control instructions may be used to instruct the automatic control system 140 to perform the second operation. As previously described, the automatic control system 140 may be a distributed control system (Distributed Control System, DCS). As shown in FIG. 5, the automated control system 140 may include a command dispatch processor 140-1 and a plurality of logic programmable controllers (Program Logic Controller, PLCs) located at the electrolysis process site, 140-2, 140-3, 140-4.… … each of which may control one or more production facilities to perform a second operation. For example, the logic programmable controller 140-2 may control the production devices 140-2a, 140-2b, and 140-2c to perform the second operation. As another example, the logic programmable controller 150-3 may control the production device 140-3a to perform a second operation.

In some embodiments, the production facility may include, but is not limited to, automated addition devices for adding electrolyte additives, automated acquisition devices for automatically acquiring data, circulation pumps and valves, and the like.

The second operation is a production operation performed by the production device. Different production facilities may correspond to different second operations. For example, a corresponding second operation of the automatic addition device may include adding a specific dose of a specific additive. For another example, the second operation corresponding to the automatic acquisition device may include acquiring specific data. For another example, the corresponding second operation of the circulation pump may include adjusting the power and the circulation amount.

Illustratively, after the automatic control system 140 receives the control command, the scheduling processor 140-1 may send a control command "shoot an image of the interior of the heat exchanger H" to the logic programmable controller 140-2 of the electrolytic process field control inspection robot, the logic programmable controller 140-2 may send the control command to the inspection robot 140-2b near the heat exchanger H based on the distance-first logic, the inspection robot 140-2b may be positioned near the heat exchanger H based on the control command, open the heat exchanger H, then shoot and acquire image data of the interior of the heat exchanger H, and send to the target command center.

Still another example, after the automatic control system 140 receives the control command, the scheduling processor 140-1 may send a control command "add 5kg hydrochloric acid to the electrolytic cell D" to the logic programmable controller 140-3 of the automatic adding device of the electrolytic process field control electrolytic cell D, the logic programmable controller 140-3 may send the control command to the automatic adding device 140-3a of the electrolytic cell D based on the identification D in the control command, and the automatic adding device 140-3a may automatically add 5kg hydrochloric acid based on the control command.

In some embodiments, the control instructions may also be used to instruct a field producer wearing AR glasses to perform a third operation. In some embodiments, the third operation may be an operation that the automatic control system is unable to perform and/or is not set. For example, the heat exchanger is turned on. For another example, 5kg of hydrochloric acid is added to the electrolytic cell D.

As described above, the first data acquisition unit may plan a patrol route from the current position of the on-site producer to the target position of patrol, and further, the AR glasses may display a navigation arrow corresponding to the patrol route to the on-site producer. In some embodiments, when the control instruction is to go to a certain position for operation, the AR glasses may display a navigation arrow from the current position of the on-site producer to the target position for inspection to the on-site producer, wherein the determination manner of the inspection route corresponding to the navigation arrow is referred to the related description of the first data acquisition unit.

In some embodiments, the AR glasses may display instructions or specifications of the operation to which the control instructions correspond to the on-site producer. The AR glasses can shoot the operation process of the on-site producer through the camera and send the operation process to the target command center.

For example, the AR glasses may generate a virtual guide identifier pointing to the electrolytic cell D based on the control instruction "add 5kg hydrochloric acid to the electrolytic cell D", guide the on-site producer to the position of the electrolytic cell D, further, the AR glasses may display the operation procedure of adding hydrochloric acid to the on-site producer, and take a photograph of the operation procedure of the on-site producer through the camera to send to the target command center.

In some embodiments, the control instructions may also be used to obtain raw material data from the internet of things platform. For example, the internet of things platform receives the control command "obtain electrolyte components of the electrolytic tank D", and may send the electrolyte components of the electrolytic tank D (e.g., 60% hydrochloric acid solution) to the target command center.

In some embodiments, after the production control unit 220 completes the production process at the control site, the data acquisition unit 210 will again send electrolysis data or reference data to the target command center, and the expert group determines whether to resolve the anomaly based on the obtained electrolysis data or reference data, if so, remote assistance is completed, otherwise, the problem type is updated again and/or the expert group is updated.

Some embodiments of the present disclosure accomplish control of an on-site electrolysis process based on remote assistance of an automatic control system, AR glasses, an internet of things platform, and an expert group, not only can determine a control scheme from multiple dimensions, but also can determine a model based on a scheme in an expert opinion training simulation system, so that the simulation system can continuously learn an expert's guidance scheme, and finally complete intelligent automatic control of the electrolysis process is achieved.

In some embodiments, the system 300 may also be used to implement electrolytic process commissioning.

For example, the target command center may send electrolyte configuration instructions to the AR glasses based on the commissioning scenario, a field worker wearing the AR glasses may complete the configuration of the electrolyte based on the protocol of the electrolyte configuration instructions, and send image data of the electrolyte configuration process to the target command center through the AR glasses.

For example, the target command center may send a voice command for valve opening and closing control to a site producer wearing AR glasses based on headphones of the AR glasses; or a control instruction is sent to the automatic control system so as to control the opening and closing of the valve, thereby completing the tightness test of the production equipment.

For example, the target command center may send a circulation pump load instruction to the AR glasses or the automatic control system based on the commissioning plan, thereby controlling the power and flow of the circulation pump; meanwhile, the AR glasses scan the two-dimensional code based on the circulating pump load instruction, acquire the running parameters of the current circulating pump from the internet platform and send the running parameters to the target command center, or the automatic control system controls the production detection device to detect the running parameters of the current circulating pump based on the circulating pump load instruction and send the running parameters to the target command center.

In some embodiments, the target command center determines whether to complete the commissioning based on data obtained from the AR glasses, the automated control system, and/or the internet of things platform.

In some embodiments, the simulation system may also train the commissioning scenario determination model based on the multiple historical commission commissioning scenarios and multiple instructions sent by the target command center, thereby achieving intelligent commissioning. For a description of the training production scenario determination model, reference may be made to the scenario determination model, which is not described in detail herein.

FIG. 4 is an exemplary flow chart for obtaining at least one update issue type according to some embodiments of the present description. In some embodiments, fig. 4 may be performed by production control unit 230.

As shown in fig. 4, the process 400 of obtaining at least one update issue type includes:

and step 410, obtaining reference opinion of the expert group of the target command center based on the electrolysis data.

As previously described, the reference opinion is the opinion of each expert member of the expert group. The related description of the obtaining reference opinion may refer to the production control unit 230 and the related description thereof, and will not be repeated herein.

At step 420, at least one alternative updated question type is generated based on the expert group's reference opinion and the at least one question type.

In some embodiments, production control unit 230 may generate at least one alternative update issue type via a text processing model. Specifically, the text processing model may fuse the input reference opinion of the expert group with the at least one question type to obtain fused information, and then output a text of at least one alternative updated question type based on the fused information.

In some embodiments, the text processing model may include, but is not limited to, a Long Short-Term Memory (LSTM) model, a Bi-directional Long Short-Term Memory (Bi-LSTM) model, a ELMo (Embedding from Language Models) model, a GPT (generating Pre-tracking) model, a BERT (Bidirectional Encoder Representation from Transformers) model, and the like.

The text processing model may be obtained through a labeled tenth training sample. The tenth training sample may include historical expert reference opinion text and at least one historical question type, and the label of the tenth training sample may include an updated question type confirmed by the historical expert.

For example, based on the expert group's reference opinion that "circulation pump power is too low, resulting in insufficient electrolyte circulation, so that the temperature is too high", "heat exchanger fails, resulting in no cooling of the electrolyte, so that the temperature is too high", "irrelevant to circuit problems", and at least one of the initial problem types "electrolyte temperature problem", at least one of the alternative update problem types "electrolyte temperature problem caused by abnormality of circulation pump flow" and "electrolyte temperature problem caused by heat exchanger failure" may be generated.

Step 430, regarding the at least one alternative update issue type as the at least one update issue type based on the validation of the expert group.

In some embodiments, production control unit 230 may send at least one alternative update issue type to the expert group via the target command center, which may be based on the voting mechanism as the at least one update issue type. For example, at least one alternative update issue type exceeding 2/3 of the number of votes is taken as the at least one update issue type. For another example, at least one alternative update issue type for at least one ticket of the acquiring expert is taken as the at least one update issue type.

Illustratively, if the alternative update problem type "electrolyte temperature problem caused by heat exchanger failure" acquires an expert vote exceeding 2/3 expert group, the "electrolyte temperature problem caused by heat exchanger failure" is taken as the update problem type.

Possible benefits of embodiments of the present description include, but are not limited to: (1) The automatic control system can control parameters in the electrolysis process more accurately, so that the product quality is improved; meanwhile, the labor cost can be reduced; (2) The target command center and the expert group are used for remote coordination, so that expert resources can be effectively utilized, and the shortage of technical talents caused by regional limitation is solved; (3) The expert group members are determined and updated based on the electrolysis data, so that on one hand, the abnormal condition of the electrolysis process can be solved in a targeted manner, and on the other hand, the waste of expert resources can be avoided; (4) The target command center can realize remote and on-site collaborative operation through the AR glasses and the automatic control system, timely performs on-site operation based on the fed-back expert guiding comments, and timely updates the expert guiding comments based on-site operation.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A remote coordinated electrolysis control system, the system comprising:

The first data acquisition unit is used for acquiring field inspection data, wherein the field inspection data is acquired based on the photographing of AR glasses worn by field producers, and the field inspection data is acquired on the field of inspection electrolysis process;

the second data acquisition unit is used for acquiring equipment production data corresponding to the field inspection data based on time based on the field inspection data, wherein the equipment production data is derived from an internet of things data platform connected with the system, and the equipment production data is automatically generated in the operation process of production equipment of an electrolysis process and comprises temperature data in the electrolysis process of an electrolytic tank and flow data in the operation process of a circulating pump;

the transmission judging unit is used for judging whether to transmit electrolytic data to a target command center or not based on the field inspection data and the equipment production data, wherein the distance between the target command center and the field exceeds a threshold value, and the electrolytic data further comprises raw material data;

the data transmission unit is used for responding to the judgment result of yes and sending the electrolysis data to the target command center; and

a production control unit for generating a control instruction based at least on the guidance opinion acquired from the target command center, and transmitting the control instruction to the AR glasses so that the on-site producer wearing the AR glasses controls the production process on the site based on the control instruction; wherein,

The determining whether to transmit electrolysis data to a target command center based on the on-site inspection data and the equipment production data includes:

determining, based on the electrolysis data, at least one initial problem type by a first model;

determining at least one updated question type based on the initial question type and expert group reference opinion;

determining a difficulty level of the at least one update issue type;

based on the difficulty level and a first preset condition, sending the electrolysis data to an updated expert group; wherein,

the determining the difficulty level of the at least one update issue type includes:

determining the difficulty level of the at least one updated problem type through a second model, wherein the second model comprises a first judgment layer, a second judgment layer and a coefficient output layer, the input of the first judgment layer comprises the field inspection data and the at least one updated problem type, and the output comprises at least one first difficulty coefficient; the input of the second decision layer comprises the equipment production data and the at least one updated problem type, and the output comprises at least one second difficulty coefficient; the input of the coefficient output layer comprises the at least one first difficulty coefficient and at least one second difficulty coefficient, and the output comprises the difficulty coefficient of the at least one updated problem type.

2. The system of claim 1, further comprising a reference data acquisition unit for:

determining at least one problem type based on the electrolysis data; and

based on the at least one question type, reference data corresponding to the at least one question type is determined.

3. The system as recited in claim 1, further comprising:

and determining the electrolysis data which each expert member needs to transmit based on the difficulty level and the updated expert members in the expert group.

4. A method of remote coordinated electrolytic control, the method comprising:

acquiring field inspection data, wherein the field inspection data is acquired based on the photographing of AR glasses worn by field producers, and the field inspection data is acquired on the field of inspection electrolysis process;

acquiring equipment production data corresponding to the field inspection data based on time based on the field inspection data, wherein the equipment production data is derived from an Internet of things data platform connected with a remote cooperative electrolysis control system, and the equipment production data is automatically generated in the operation process of production equipment of an electrolysis process and comprises temperature data in the electrolysis process of an electrolytic tank and flow data in the operation process of a circulating pump;

Judging whether to transmit electrolysis data to a target command center based on the field inspection data and the equipment production data, wherein the distance between the target command center and the field exceeds a threshold value, and the electrolysis data further comprises raw material data;

responding to the judgment result of yes, and sending the electrolysis data to the target command center; and

generating control instructions based at least on the instruction opinion obtained from the target command center and transmitting the control instructions to the AR glasses so that the on-site producer wearing the AR glasses controls the production process of the on-site based on the control instructions; wherein,

determining a difficulty level of the at least one update issue type;

5. The method of claim 4, wherein the method further comprises:

determining at least one problem type based on the electrolysis data; and

6. The method as recited in claim 4, further comprising:

7. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the method of any one of claims 4 to 6.

8. A remote coordinated electrolysis control apparatus comprising at least one processor and at least one memory; the at least one memory is configured to store computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the method of any one of claims 4-6.