Method, device and equipment for controlling silk ingot quality based on knowledge graph

Abstract

The present disclosure provides a method, device and equipment for controlling the quality of silk ingots based on a knowledge graph. The method comprises: determining whether there are abnormal parameters in the production parameters and / or the process parameters of a group of silk ingots based on the quality inspection results, production parameters and process parameters of the group of silk ingots; in the case of the presence of the abnormal parameters, searching for the adjustment method corresponding to the production parameters and / or the process parameters in the silk ingot production management knowledge graph; and sending the adjustment method corresponding to the production parameters and / or the process parameters to the relevant equipment of the group of silk ingots. According to an embodiment of the present disclosure, in the case of determining that there are abnormal parameters through the quality inspection results, production parameters and process parameters of the silk ingots, the appropriate adjustment method corresponding to the production parameters and / or process parameters can be obtained based on the knowledge graph, thereby optimizing the production process of the silk ingots and obtaining silk ingot products with better quality.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, in particular to the field of industrial control, and specifically discloses a method, device and equipment for controlling silk ingot quality based on a knowledge graph. Background Art

[0002] In the chemical fiber industry, product quality inspections are essential. If substandard product quality is detected, manual adjustments to the production process may be necessary. However, even when substandard product quality is identified, determining appropriate adjustments can be challenging due to the lengthy and complex production process and the numerous factors influencing product quality. Consequently, identifying and resolving process issues requires significant manpower and time. Summary of the Invention

[0003] The present disclosure provides a method, device, equipment and storage medium for controlling silk ingot quality based on a knowledge graph to solve or alleviate one or more technical problems in the prior art.

[0004] In a first aspect, the present disclosure provides a method for controlling the quality of silk ingots based on a knowledge graph, comprising:

[0005] determining whether there are abnormal parameters in the production parameters and / or the process parameters of the group of silk ingots based on quality inspection results, production parameters, and process parameters of the group of silk ingots;

[0006] In the case where the abnormal parameter exists, searching for an adjustment method corresponding to the production parameter and / or the process parameter in the ingot production management knowledge map;

[0007] The production parameters and / or the adjustment methods corresponding to the process parameters are sent to relevant equipment of the group of ingots.

[0008] In a second aspect, the present disclosure provides a silk ingot quality control device based on a knowledge graph, comprising:

[0009] a determination module, configured to determine whether there are abnormal parameters in the production parameters and / or the process parameters of the group of silk ingots based on quality inspection results, production parameters, and process parameters of the group of silk ingots;

[0010] A search module is used to search for an adjustment method corresponding to the production parameter and / or the process parameter in the ingot production management knowledge map when the abnormal parameter exists;

[0011] The sending module is used to send the production parameters and / or the adjustment method corresponding to the process parameters to the relevant equipment of the group of ingots.

[0012] According to a third aspect, an electronic device is provided, including:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any method in the embodiments of the present disclosure.

[0016] In a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any method according to the embodiments of the present disclosure.

[0017] According to the embodiment of the present disclosure, when it is determined that abnormal parameters exist through the quality inspection results, production parameters and process parameters of the silk ingot, appropriate adjustment methods corresponding to the production parameters and / or process parameters can be obtained based on the knowledge graph, thereby optimizing the production process of the silk ingot and obtaining a silk ingot product with better quality.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments provided in accordance with the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0020] Figure 1 is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to an embodiment of the present disclosure;

[0021] Figure 2 is a schematic flowchart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0022] Figure 3 A schematic flowchart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0023] Figure 4 A schematic flowchart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0024] Figure 5 A schematic flowchart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0025] Figure 6 A schematic flowchart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0026] Figure 7 A schematic flowchart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure;

[0027] Figure 8 is a schematic diagram of a portion of a knowledge graph according to an embodiment of the present disclosure;

[0028] Figure 9 is a schematic diagram of a device knowledge framework in an embodiment of the present disclosure;

[0029] Figure 10 is a schematic diagram of a process parameter knowledge framework in an embodiment of the present disclosure;

[0030] Figure 11 1 is a schematic structural diagram of a silk ingot quality control device based on a knowledge graph according to an embodiment of the present disclosure;

[0031] Figure 12 1 is a schematic structural diagram of a silk ingot quality control device based on a knowledge graph according to an embodiment of the present disclosure;

[0032] Figure 13 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The present disclosure will be described in further detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0034] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, circuits, etc. well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0035] Figure 1 This is a schematic flow chart of a method for controlling ingot quality based on a knowledge graph according to an embodiment of the present disclosure. The method includes:

[0036] S101. Determine whether there are abnormal parameters in the production parameters and / or the process parameters of a group of silk ingots based on quality inspection results, production parameters, and process parameters of the group of silk ingots.

[0037] S102: When the abnormal parameter exists, searching for an adjustment method corresponding to the production parameter and / or the process parameter in the ingot production management knowledge graph;

[0038] S103: Sending the production parameters and / or the adjustment method corresponding to the process parameters to related equipment of the group of ingots.

[0039] In the disclosed embodiments, a group of spindles may include multiple spindles from the same batch or multiple spindles from different batches. Spindles from the same batch typically share the same parameters. For example, the same parameters for spindles from the same batch may include: fineness center value, metering pump specifications, metering pump speed, oiling rate, oil concentration, spinneret diameter, spinneret aspect ratio, assembly pressure, winding speed, winding overfeed, network pressure, wind pressure, wind speed, etc.

[0040] In the embodiments of the present disclosure, the quality inspection results of the silk ingots may include results obtained by inspecting the silk ingots using various testing equipment. For example, a Raman spectrum of the chemical fiber obtained by inspecting the chemical fiber in the silk ingot using a Raman spectrometer. Another example is a photograph of the chemical fiber in the silk ingot obtained using a scanning electron microscope. The quality inspection results may also include dye-free color determination results, appearance inspection results, physical and mechanical property inspection results, etc., obtained by analyzing the Raman spectrum and chemical fiber photographs of the chemical fiber.

[0041] For example, the dye-free color judgment result can include a prediction of the dyeing uniformity of the silk spindles based on spectral detection and other results before the silk spindles are spun and dyed. Using the dye-free color judgment result can reduce textile costs and dye waste, and improve detection efficiency.

[0042] For example, the appearance inspection results may include manual or model inspection and analysis of images such as chemical fiber photos, to determine whether the appearance of the silk spindle meets production standards, such as whether there are lint, stray wires, oil stains, or damaged paper tubes.

[0043] For another example, the physical and mechanical property test results may include the results obtained by testing the physical and mechanical properties of the silk spindle, such as: linear density deviation rate, linear density variation coefficient, breaking strength, breaking elongation, drying unevenness CV, etc.

[0044] In one embodiment, the production parameters include at least one of the following: line type, machine number, specification, batch number, drop order, and drop time.

[0045] In one embodiment, the quality inspection result includes at least one of the following: non-staining color spectrum information, non-staining color abnormality result, appearance inspection result, and physical and mechanical property inspection result.

[0046] In one embodiment, the process parameters include at least one of the following: tension, spinning speed, oil content, oil type, oil application rate, hot roller temperature, fineness center value, metering pump specifications, metering pump speed, spinneret diameter, spinneret aspect ratio, full barrel weight, and network pressure.

[0047] In the embodiment of the present disclosure, in the production parameters, the line type and machine number can indicate the production equipment of the silk ingot. The line type can indicate the production line of the silk ingot, and the machine number can indicate the number of the equipment used to produce the silk ingot in the production line. The specifications can be represented by characters or numbers, and the rules can correspond to the product type, material, size, weight, etc. of the silk ingot. The drop order can also be called the doffing number, which can indicate the order in which the silk ingot is doffed. The doffing time can indicate the time when the silk ingot product is actually doffed on the production equipment, such as the winding machine. For example, the silk ingot with the batch number "XB080516" corresponds to the winding machine with the line type and machine number "WDC 2-04". The location of this winding machine is the 4th winding machine on line 2 in the "WDC" channel. The specifications of the silk ingot are "55 / 36", the drop order of the silk ingot is "2", and the doffing time is "2023 / 06 / 05 13:26:55".

[0048] In the embodiment of the present disclosure, the process parameters of the silk ingot can be obtained according to the process actually used in the silk ingot production process. For example, among the process parameters, the center value of fineness can indicate the thickness of the yarn in the batch, and the positive and negative deviation ranges of yarns with different DPF (Denier PerFilament, unit mass per yarn) are different, such as 167±2.5%; tension can indicate the magnitude of the pulling force applied to the yarn during the production process; winding overfeed can indicate the ratio of the difference between the winding roller and the vehicle speed, which can directly affect the package size, and can be calculated as (winding speed - vehicle speed) ÷ vehicle speed × 100%; spinning speed can also include winding speed, which is related to the rotation speed of the yarn stretching roller. During the winding process, the speed at which the spinneret of the spinning box ejects the fiber is generally consistent with the spinning speed. For example, the spinning speed can be 2710M / min-2715M / min; oil content can indicate the weight proportion of the oil in the overall mass of the yarn; hot roller temperature can indicate the temperature of the hot roller that heats the chemical fiber. For example, the pre-heating hot roller temperature can be 94±2°C, and the main heating hot roller temperature can be 143±2°C.

[0049] In the disclosed embodiments, the production parameters and / or process parameters of one or more ingots can be recorded in a server, such as a single ingot data stream system or an ingot lifecycle system. The production parameters and / or process parameters of different ingots may differ, or they may be the same for multiple ingots. Using the batch number of an ingot, the production parameters and / or process parameters of ingots with the same batch number can be retrieved from the server.

[0050] In an embodiment of the present disclosure, an anomaly detection model or knowledge graph can be used to determine whether any abnormal parameters exist in the production parameters and / or process parameters of a group of silk ingots based on the quality inspection results, production parameters, and process parameters of the group of silk ingots. The anomaly detection model or knowledge graph can include a normal parameter range. If a production parameter and / or a process parameter is within the normal parameter range, it indicates that the production parameter and / or the process parameter is a normal parameter. If a production parameter and / or a process parameter is not within the normal parameter range, it indicates that the production parameter and / or the process parameter is an abnormal parameter.

[0051] In the disclosed embodiments, abnormal parameters may include abnormal production parameters and abnormal process parameters. For example, if the temperature of a hot roller in a spinning spindle is abnormal, the knowledge graph can be used to search for corresponding equipment information based on the machine to which the abnormal hot roller belongs. This can then determine the cause of the abnormal hot roller temperature on that machine, such as a temperature sensor failure, a hot roller heating rod failure, a circuit abnormality, or a controller failure. For another example, if a "hot roller heating rod failure" is identified, the knowledge graph can be searched for the cause and corresponding solution for this "hot roller heating rod failure." The search results will be sorted and displayed by frequency or time.

[0052] In the disclosed embodiment, process parameter abnormalities include abnormal tension, abnormal spinning speed, abnormal oil content, and abnormal hot roller temperature. For example, if the oil content in the process parameters of a silk spindle is abnormal, the normal range of the oil content can be found in the knowledge graph. Based on the normal range of the oil content, a method for adjusting the oil content of the production equipment of the silk spindle (for example, it can be determined based on parameters such as the machine number of the silk spindle) is given. For another example, if the spinning speed in the process parameters of a silk spindle is abnormal, the normal range of the spinning speed can be found in the knowledge graph, and the normal range of the spinning speed can be displayed, and a method for adjusting the spinning speed can also be given.

[0053] In one embodiment, the group of related equipment of the ingots includes at least one of the following: production equipment; terminal equipment; control equipment.

[0054] In the disclosed embodiment, the adjustment method can be sent to the relevant equipment corresponding to a group of spindles. After receiving the adjustment method, the relevant equipment can display the adjustment method or automatically adjust according to the corresponding adjustment method. The adjustment method can include the cause of the fault, the solution, and the maintenance suggestion.

[0055] For example, adjustments can be sent to a group of spindles corresponding to production equipment such as reactors, spinning beams, or winders. The equipment can then display the cause of the fault, a solution, and repair suggestions, and can also automatically adjust certain parameters within the equipment.

[0056] For another example, when the abnormal parameter is "device A failure", the cause and solution of "device A failure" are sent to the maintenance personnel's terminal device such as a personal digital assistant (PDA), and the cause and solution are displayed on the PDA, and maintenance suggestions are given.

[0057] For another example, if a production workshop is equipped with a control device, such as a Data Center Interconnect (DCI), for controlling the operation of multiple production devices, a set of adjustment methods corresponding to the production parameters and / or process parameters of the silk ingot can also be sent to the control device. The control device can then adjust the equipment and / or process designed for the production parameters and / or process parameters that need to be adjusted.

[0058] According to an embodiment of the present disclosure, when abnormal parameters are determined through the quality inspection results, production parameters, and process parameters of the silk spindle, appropriate adjustment methods corresponding to the production parameters and / or process parameters can be obtained based on the knowledge graph, thereby optimizing the production process of the silk spindle and obtaining a silk spindle product with better quality. For example, when it is determined that the oil content is abnormal, the line type and machine number of the production equipment corresponding to the silk spindle are obtained based on the knowledge graph, and the normal oil content range and adjustment method are obtained. Based on the line type and machine number of the production equipment and the normal oil content range, the adjustment method is displayed on the control interface of related equipment such as the spinning box, which facilitates maintenance personnel to efficiently and quickly solve problems in the production process.

[0059] Figure 2 This is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the aforementioned method for controlling silk ingot quality based on a knowledge graph. In one embodiment, the group of silk ingots includes a group of silk ingots of the same batch number. S101: Based on the quality inspection results, production parameters, and process parameters of the group of silk ingots, determining whether there are abnormal parameters in the production parameters and / or process parameters of the group of silk ingots includes:

[0060] S201: If the quality inspection result is abnormal, determine whether the production parameters and / or process parameters of the group of ingots are within a normal range based on the ingot production management knowledge graph;

[0061] S202: Acquire abnormal parameters that are not within a normal range from the production parameters and / or process parameters of the group of ingots.

[0062] In the disclosed embodiment, a determination can be made based on an anomaly detection model to determine whether the quality inspection result of the silk ingot is abnormal. If the quality inspection result is abnormal, the step of determining abnormal parameters is performed to determine whether the production parameters and / or process parameters of the silk ingot are within the normal range corresponding to the batch number of the silk ingot based on the silk ingot production management knowledge graph. If the production parameters and / or process parameters of the silk ingot are not within the normal range corresponding to the batch number of the silk ingot, the production parameters and / or process parameters that are not within the normal range are then obtained.

[0063] In the embodiment of the present disclosure, when there is an abnormality in the quality inspection result, the production parameters and / or process parameters of the silk spindle are determined to be within the normal range of the batch number corresponding to the silk spindle based on the silk spindle production management knowledge map, and the step of determining the abnormal parameters is not performed. Since there are many uncontrollable factors in the chemical fiber production process, and the environment will also affect the quality of the final product, when there is an abnormality in the quality inspection result, the production parameters and / or process parameters are not necessarily abnormal. For example, the abnormality of the inspection result is caused by factors other than production and process. In the above case, the production parameters and / or process parameters do not need to be adjusted.

[0064] According to the embodiments of the present disclosure, by further verifying the production parameters and / or process parameters when there are abnormalities in the quality inspection results, and obtaining the abnormal parameters in the production parameters and / or process parameters, the efficiency of verifying the abnormal parameters can be improved, the number of inspections can be reduced, and the inspection speed can be increased. Furthermore, when there are no abnormalities in the quality inspection results, further verification of the abnormal parameters can be omitted, thereby avoiding frequent adjustments to the production parameters and / or process parameters, increasing the stability of the production process, and facilitating the consistency of product quality.

[0065] Figure 3 This is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the above-mentioned method for controlling silk ingot quality based on a knowledge graph. In one embodiment, the method further includes:

[0066] S301. When the quality inspection result is normal, the quality inspection result, the production parameters, and the process parameters of the group of ingots are saved in the ingot production management knowledge graph.

[0067] In the disclosed embodiment, when the quality inspection results are normal, the process parameters corresponding to the ingot can be considered to be the normal values ​​of the production parameters for the corresponding batch of ingots. The quality inspection results, production parameters, and process parameters for the group of ingots can be recorded in the knowledge graph. After a period of statistical analysis, the normal range of parameters can be updated using the statistically normal production parameters and process parameters. Furthermore, process parameters are linked to production parameters, and the normal range of corresponding process parameters may vary for each piece of production equipment depending on the actual conditions of the equipment.

[0068] In this disclosed embodiment, if the number of abnormal quality inspection results reaches a set value, but no abnormal parameters exist, an emergency inspection task can be initiated to inspect the equipment corresponding to the ingot. If the equipment is faulty, the knowledge graph can be used to identify appropriate adjustments. If the equipment is not faulty, the normal range can be updated based on the newly stored production and process parameters in the knowledge graph.

[0069] In the disclosed embodiment, if the quality inspection results are abnormal, and the abnormal parameter is determined to be a production parameter, it indicates that at least one of equipment failure, spare part failure, equipment loss, or equipment downtime has occurred. After the repair is completed, the abnormal parameter, the cause of the abnormal parameter, and the repair method can be recorded. The abnormal parameter, the cause of the abnormal parameter, and the repair method can be used to update the data in the ingot production management knowledge graph.

[0070] According to the embodiment of the present disclosure, the normal range of the original process parameters is updated by using process parameters within the new normal range, thereby improving the accuracy of the process parameters; each production equipment can dynamically optimize its own production parameters during continuous updates to ensure product quality; and the adjustment methods corresponding to abnormal production parameters can also be continuously entered to improve the knowledge map of silk ingot production management.

[0071] Figure 4 This is a schematic flow chart of a method for controlling ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the aforementioned method for controlling ingot quality based on a knowledge graph. In one embodiment, S102, when the abnormal parameter exists, searches the ingot production management knowledge graph for an adjustment method corresponding to the production parameter and / or the process parameter, including:

[0072] S401, searching the ingot production management knowledge graph for normal process parameters corresponding to the abnormal parameter, and determining a process adjustment method based on the normal process parameters;

[0073] S402: searching for device information corresponding to the abnormal parameter in the ingot production management knowledge graph, and determining the faulty device and the corresponding adjustment method based on the device information and the adjustment method.

[0074] In the embodiment of the present disclosure, if the abnormal parameter is a process parameter, the normal range of the process parameter can be found in the silk spindle production management knowledge map based on the abnormal process parameter. The corresponding adjustment method can be given based on the normal range of the process parameter. For example, the abnormal spinning speed of a certain batch of silk spindles when wound on a certain type of winding machine is 2400M / min, and the normal range in the abnormal detection model or knowledge map is 2700M / min to 2705M / min. It can be recommended to increase the spinning speed based on the normal range, and the specific value that needs to be increased can also be given. The adjusted process parameters can be used to produce silk spindles in the next production; when the spinning speed of a certain batch of silk spindles when wound on a certain type of winding machine is 2702.1M / min, the spinning speed of this production is normal.

[0075] In the disclosed embodiment, if the abnormal parameter is an equipment parameter, the corresponding equipment information can be searched in the ingot production management knowledge graph based on the abnormal equipment parameter. Furthermore, process parameters and equipment parameters for the same group of ingots can have a corresponding relationship. If the abnormal parameter is a process parameter, the corresponding equipment information can be searched in the ingot production management knowledge graph based on the equipment parameter corresponding to the abnormal process parameter.

[0076] According to the embodiments of the present disclosure, combined with the knowledge graph, it is possible to obtain both specific abnormal parameters and the adjustment methods corresponding to the abnormal parameters, quickly determine the source of the problem leading to poor product quality, and provide solutions to the problem, which is beneficial to improving the error correction and quality monitoring capabilities in the chemical fiber production process, improving the qualified rate and quality of products, reducing the amount of waste, reducing production costs, and improving production efficiency.

[0077] In one embodiment, the equipment information corresponding to the abnormal parameter includes at least one of the following: equipment and / or components that require maintenance; upstream and downstream associated equipment and / or components of the equipment and / or spare parts that require maintenance; maintenance records of equipment and / or components that require maintenance; storage information of spare equipment and / or spare parts; and procurement information of spare equipment and / or spare parts.

[0078] In the disclosed embodiment, if the abnormal equipment parameters include a line number and a machine number, or if the equipment parameters corresponding to the abnormal process parameters include a line number and a machine number, the knowledge graph can be used to find equipment requiring maintenance, such as faulty equipment, based on the line number and machine number. The knowledge graph can also include spare parts for the equipment requiring maintenance, such as faulty spare parts.

[0079] In the disclosed embodiments, upstream and downstream associated equipment may be equipment in the production process that is a precursor to and / or a subsequent stage of the production process corresponding to the equipment requiring maintenance. For example, the downstream equipment of a spinning manifold includes a winder. Upstream and downstream associated spare parts may be spare parts in the upstream and downstream associated equipment of the equipment requiring maintenance. Product quality issues may also be caused by the upstream and downstream associated equipment / spare parts of a particular piece of production equipment. Identifying these upstream and downstream associated equipment / spare parts facilitates accurate location of the problematic equipment.

[0080] In the disclosed embodiments, maintenance records for equipment / spare parts requiring maintenance may include one or more items, such as the equipment / spare part name, fault name, fault cause, fault time, fault frequency, repair time, repair method, and repair frequency. The need for equipment and / or spare part replacement can be determined based on the equipment's previous maintenance records. For example, if a spinneret's oil nozzle has been repaired three times, reaching a maintenance frequency threshold, a recommendation may be made to replace the nozzle.

[0081] In the embodiments of the present disclosure, the storage information of the equipment and / or spare parts requiring maintenance includes one or more of the equipment / spare part name, brand, model, specifications, storage location, storage quantity, entry time, exit time, and the factory where it is purchased. The procurement information of the equipment and / or spare parts requiring maintenance includes one or more of the equipment / spare part name, brand, model, specifications, factory exit time, number of purchases, purchaser, price, supplier, and procurement quantity.

[0082] According to the embodiments of the present disclosure, various information required during the maintenance of equipment or spare parts can be obtained, providing data support and basis for generating equipment adjustment methods such as equipment maintenance strategies, thereby improving the rationality and reliability of maintenance strategies.

[0083] In one embodiment, determining a device adjustment method based on the device information includes: initiating a maintenance task based on the device information corresponding to the abnormal parameter. Examples of the maintenance task include at least one of the following:

[0084] Example 1: Based on the maintenance records of the equipment and / or components that need maintenance, determine the maintenance method corresponding to the equipment and / or components that need maintenance; based on the maintenance method, initiate a maintenance task for the faulty equipment and / or faulty components to the maintenance management device, and the maintenance task includes the identification of the faulty equipment and / or faulty components.

[0085] In the embodiment of the present disclosure, the maintenance method may include repairing a certain component of the equipment, replacing a certain component with a spare part, etc. Based on the maintenance method, the maintenance task may include not only the identification of the component that needs to be repaired and / or the faulty component, but also the storage information of the replacement equipment and / or spare parts needed to repair a certain faulty equipment. According to the maintenance strategy, the corresponding equipment and / or spare parts are shipped out of the warehouse and transported to the location of the faulty equipment. For example, the following record exists in the knowledge graph for equipment A that needs repair: Component A1 of equipment A has failed twice, and there are 3 spare parts for component A1 in the warehouse B. In this case, the generated maintenance strategy can be to replace component A1, and the maintenance strategy can be sent to the maintenance personnel's PDA, and the spare parts of component A1 can be shipped out of warehouse B and transported to the vicinity of equipment A.

[0086] Example 2: When the local inventory of spare equipment and / or spare parts is lower than the safety threshold, a procurement task for spare equipment and / or spare parts is initiated to the procurement management system, and the procurement task includes procurement information of the equipment and / or spare parts to be purchased.

[0087] In some examples, there may be multiple warehouses required for chemical production. Local warehouses may include warehouses that are close to the equipment that needs repair, or warehouses that equipment maintenance personnel have access rights to. Off-site warehouses may include warehouses that are far away from the equipment that needs repair, or warehouses that equipment maintenance personnel do not have access rights to. The local inventory may be the number of spare equipment and / or spare parts included in the local warehouse, and the off-site inventory may be the number of spare equipment and / or spare parts included in the off-site warehouse. In the embodiment of the present disclosure, the local inventory may also include a set number of equipment and / or spare parts. When the number of equipment and / or spare parts is lower than the set number, a purchase demand for equipment and / or spare parts is initiated to the procurement management system, and after confirming the purchase demand, a purchase task is issued to the supplier.

[0088] Example 3: When the local inventory of spare equipment and / or spare parts is lower than the safety threshold, check whether the spare equipment and / or spare parts exist in the off-site inventory; if so, initiate an adjustment task to the off-site warehouse management device, which includes the inventory information of the equipment and / or spare parts that need to be adjusted.

[0089] In the disclosed embodiment, inventory quantity and distance can be comprehensively calculated to prioritize the initiation of transfer tasks to the warehouse management equipment of the nearest remote warehouse. If multiple remote warehouses exist with distance differences within a distance threshold, the transfer task is prioritized to the warehouse management equipment of the remote warehouse with the larger inventory quantity.

[0090] Example 4: When the local and remote inventories of spare equipment and / or spare parts are both below the safety threshold, an emergency processing task is initiated. The emergency processing task includes an emergency procurement task and / or an idle equipment loan task.

[0091] In an embodiment of the present disclosure, when both local inventory and off-site inventory cannot meet maintenance needs, an emergency processing task can be initiated. For example, if there are idle devices of the same model in the local production line, a borrowing task can be initiated to the control device or the computer, PDA, etc. of the relevant personnel. Then, the idle equipment and / or the spare parts in the idle equipment can be removed from the original location to replace the faulty equipment and / or the faulty spare parts in the faulty equipment. If the borrowing task is executed, the borrowing information can be recorded in the knowledge graph. For another example, if there are no idle devices in the local production line, an emergency procurement task can be initiated to the control device or the computer, PDA, etc. of the relevant personnel to purchase the corresponding equipment and / or spare parts. The procurement task may include one or more of the name of the equipment / spare parts to be purchased, brand, specification model, key parameters, purchaser, price, supplier, and purchase quantity.

[0092] According to the disclosed embodiments, reliable solutions can be provided for maintenance tasks and various possible situations, ensuring that maintenance tasks are completed normally and efficiently, improving maintenance efficiency and reducing economic losses caused by long maintenance times. Furthermore, the flexibility of maintenance strategies can be increased by utilizing maintenance tasks to adjust or loan equipment and / or spare parts.

[0093] Figure 5 This is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the above-mentioned method for controlling silk ingot quality based on a knowledge graph. In one embodiment, the method further includes:

[0094] S501: Construct one or more ingot production management knowledge frameworks, and establish association relationships between the one or more ingot production management knowledge frameworks; wherein the ingot production management knowledge framework includes one or more slots;

[0095] In the disclosed embodiment, the ingot production management knowledge graph includes multiple frames, each frame includes multiple slots, and each slot corresponds to multiple slot values; wherein each frame has a certain correlation relationship. For example, both the production parameter knowledge frame and the process parameter knowledge frame may include a batch number slot, and a correspondence can be established between the two through the batch number slot. Through the batch number, product specifications, production equipment, production time, various process parameters, etc. can be queried. For another example, the production parameter knowledge frame includes a batch number slot, and the process parameter knowledge frame includes a tension slot and a spinning speed slot. Through indexing, a correspondence between the batch number slot, the tension slot, and the spinning speed slot in the two knowledge frames can be established.

[0096] S502: Based on the single spindle data flow system, the quality feedback model, the maintenance records and the storage data, the silk spindle production management knowledge data is obtained.

[0097] In the disclosed embodiment, the spindle production management knowledge data includes at least one of production parameter data, quality inspection result data, process parameter data, and equipment information data. The production parameter data may include line data, machine number data, specification data, batch number data, drop data, drop time data, etc. The production parameter data may be obtained through a single spindle data stream system, a spindle life cycle system, etc. The quality inspection result data may include dye-free color spectrum information data, dye-free color abnormality result data, appearance inspection result data, physical and mechanical property inspection result data, etc. The quality inspection result data may be obtained through Raman spectroscopy equipment, etc. The process parameter data may include tension data, spinning speed data, oil content data, oil model data, oil application rate data, hot roller temperature data, fineness center value data, metering pump specification data, metering pump speed data, spinneret diameter data, spinneret aspect ratio data, full barrel weight data, network pressure data, etc. The process parameter data may be obtained through actual measurement or pre-configuration. Equipment information data may include equipment name data, equipment tag data, fault name data, fault cause data, fault time data, fault frequency data, maintenance time data, maintenance method data, maintenance frequency data, storage location data, storage quantity data, storage time data, storage time data, storage time data, factory ownership data, etc. Equipment information data can be obtained through maintenance records and storage data.

[0098] S503 , fusing the silk ingot production management knowledge data, setting the fused silk ingot production management knowledge data as the slot values ​​of the one or more slots in the one or more silk ingot production management knowledge frameworks, and obtaining the silk ingot production management knowledge graph.

[0099] In the disclosed embodiment, the fusion of ingot production management knowledge data may include cleaning the obtained data, clustering the cleaned data, and storing them in different knowledge frameworks. For unstructured data, the data may be segmented and deduplicated, and the processed data may be clustered. The clustered data are respectively set as slot values ​​in different knowledge frameworks. For structured data, the data may be disambiguated and deduplicated, wherein disambiguation may include storing one of the data with different attribute names but representing the same meaning; or disambiguation may also include renaming the attribute names of the data with the same attribute names but representing different meanings, and storing them separately; deduplication may include storing one of the data with the same attribute names and representing the same meaning. The processed structured data is stored in the knowledge graph according to the correspondence between the attribute names and the slot names.

[0100] According to the disclosed embodiments, a knowledge graph for spindle production management can be constructed based on various data involved in the chemical fiber production process, ensuring the reliability and credibility of the knowledge graph. Using this knowledge graph, data from different systems within the factory can be linked and integrated, simplifying query steps and improving query efficiency. Furthermore, the knowledge graph can be updated with new data from the production process, improving its timeliness.

[0101] In one embodiment, the one or more ingot production management knowledge frameworks include a production parameter knowledge framework, an inspection result knowledge framework, a process parameter knowledge framework, an equipment information knowledge framework, an equipment maintenance record framework, and associations between the various knowledge frameworks.

[0102] In one embodiment, the production parameter knowledge framework includes a specification slot, a batch number slot, a drop slot, and a drop time slot; the inspection result knowledge framework includes a non-dye color judgment spectrum information slot, a non-dye color judgment abnormality result slot, an external detection result slot, and a physical and mechanical property detection result slot; the process parameter knowledge framework includes a tension slot, a spinning speed slot, an oil content slot, an oil model slot, an oil application rate slot, a hot roller temperature slot, a fineness center value slot, a metering pump specification slot, a metering pump speed slot, a spinneret diameter slot, a spinneret aspect ratio slot, a full barrel weight slot, and a network pressure slot; the equipment information knowledge framework includes a line identification slot, a machine number slot, an equipment name slot, an equipment type slot, a storage information slot, a spare parts slot, and a maintenance record slot; the equipment maintenance record knowledge framework includes an equipment name slot, an equipment position number slot, a fault / alarm information slot, and a maintenance information slot.

[0103] In the disclosed embodiments, a slot can correspond to multiple slot values. For example, in the production parameter knowledge framework, the slot value of the specification slot is one or more specification data, the slot value of the batch number slot is one or more batch number data, the slot value of the drop slot is one or more drop data, and the slot value of the doffing time slot is one or more doffing time data. Similarly, the slot values ​​in the inspection result knowledge framework, process parameter knowledge framework, and equipment information knowledge framework are the corresponding data after fusion.

[0104] In the disclosed embodiment, multiple production parameters and process parameters corresponding to a group of ingots may be distributed in different slots of multiple knowledge frameworks, and there is an association relationship between the slots corresponding to the parameters of the group of ingots.

[0105] According to the disclosed embodiments, by establishing relationships between frames, slots, and slot values, data relevance and queryability can be enhanced. By using multiple frames with multiple slots, various data involved in the production process can be stored in a categorized manner, improving the organization of data in the knowledge graph.

[0106] Figure 6This is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the above-mentioned method for controlling silk ingot quality based on a knowledge graph. In one embodiment, it further includes:

[0107] S601: Input the quality inspection result, the production parameter, and the process parameter of the multi-spindle silk ingot into a quality feedback model to obtain the product status of the multi-spindle silk ingot.

[0108] In the disclosed embodiments, Raman spectroscopy equipment can be used to inspect the chemical fiber of a silk ingot to obtain quality inspection results. Based on the production and process parameters obtained from the quality inspection results, the quality inspection results are input into a quality feedback model to determine the product status of the silk ingot. Alternatively, the quality inspection results, production parameters, and process parameters can be input into the quality feedback model to determine the product status of the silk ingot.

[0109] In one embodiment, the product status includes at least one of a yield rate, a full roll rate, and a broken end rate.

[0110] In the embodiment of the present disclosure, the yield rate may include the ratio of the number of silk spindles in a group of silk spindles that meet the quality requirements to the total number of silk spindles. Among them, the quality requirements of a group of silk spindles may include appearance performance meeting the standards, physical and mechanical properties meeting the standards, dyeing performance meeting the standards, and silk spindle weight meeting the standards. The full roll rate may include the ratio of the number of silk spindles in a group of silk spindles that reach full roll to the total number of silk spindles. Full roll silk spindles include silk spindles that have no broken wires, no silk path abnormalities, and the spindle weight meets the full roll requirements during the winding process. The broken end rate may include the total number of broken ends in a production line or a winding machine within a fixed time divided by the fixed time. The yield rate can also be called the AA rate, which represents the proportion of AA products in a batch. The AA rate can also be called the superior product rate, and the calculation method can be: AA product weight / total output of the batch = AA%.

[0111] In the disclosed embodiments, a quality feedback model can be used to determine the quality of ingots based on quality inspection results, production parameters, and process parameters, improving the efficiency of ingot quality inspection. Using the quality feedback model to inspect ingot quality eliminates the need to consume ingots to produce inspection samples, saving inspection costs. The quality feedback model can be used to inspect each ingot, improving the reliability of quality inspection results.

[0112] Figure 7 This is a schematic flow chart of a method for controlling silk ingot quality based on a knowledge graph according to another embodiment of the present disclosure. The method may include one or more features of the above-mentioned method for controlling silk ingot quality based on a knowledge graph. In one embodiment, it further includes:

[0113] S701. When the product status of the multi-spindle silk ingots output by the quality feedback model meets the qualified threshold, trigger the execution of S101. That is, based on the quality inspection results, production parameters and process parameters of a group of silk ingots, determine whether there are abnormal parameters in the production parameters and / or process parameters of the group of silk ingots. The number of multi-spindle silk ingots input into the quality feedback model and the number of a group of silk ingots can be the same or different. For example, the quality inspection results, production parameters and process parameters of 1000 silk ingots are input into the quality feedback model, and the yield rate does not meet the quality requirements. This group of 1000 silk ingots can be divided into 2 groups, and the production parameters and / or process parameters of each group of silk ingots can be detected separately to determine whether there are abnormal parameters.

[0114] In the disclosed embodiment, whether a group of ingots meets product qualification standards can be determined based on at least one of their yield rate (AA rate), full roll rate, and end-breakage rate. If the ingots do not meet product qualification standards, a knowledge graph is used to verify whether abnormal parameters occurred during the production of the ingots. If abnormal parameters exist, adjustment methods corresponding to the abnormal parameters are obtained based on the knowledge graph. If no abnormal parameters exist, no production or process parameters are adjusted, allowing detection of other issues that may have caused the abnormal parameters.

[0115] According to the embodiment of the present disclosure, when the silk ingots do not meet the product qualification standards, the abnormal parameter inspection process is carried out, and there is no need to inspect all the silk ingots, which reduces the number of inspections, improves the inspection efficiency, and reduces the consumption of computing power.

[0116] In one embodiment, the training process of the quality feedback model includes:

[0117] Inputting the quality inspection results, production parameters, and process parameters of the ingot training samples in the sample set into a first model composed of a multi-layer neural network, and outputting a predicted product state;

[0118] Iteratively training the first model based on the labeled product status of the ingot training sample and the loss function constructed by the predicted product status to obtain a second model;

[0119] The sample set includes a plurality of silk ingot training samples obtained from the silk ingot production management knowledge graph, and each of the plurality of silk ingot training samples includes the mutually related quality inspection results, production parameters, and process parameters;

[0120] The second model is the trained quality feedback model.

[0121] In the embodiments of the present disclosure, a multi-layer neural network may include an input layer, an intermediate layer, and an output layer. The intermediate layer may be multi-layered. The input features of the input layer may include quality inspection results, production parameters, and process parameters. The output features of the output layer may include predicted product status. Samples in a sample set may include quality inspection results, production parameters, and process parameters, and may also include annotated product status. The annotated product status may be derived based on the actual measured product status.

[0122] In the embodiment of the present disclosure, the output layer calculates the loss value based on the labeled product status and the predicted product status, as well as the loss function. The loss value formula is as follows:

[0123] M=α1S1+α2S2+α3(1-S3)+α4(1-S4)

[0124] Where S1 represents the AA rate, S2 represents the winder efficiency, S3 represents the end-break rate, and S4 represents the equipment failure rate. α1, α2, α3, and α4 are weighting coefficients for each parameter: α1 + α2 + α3 + α4 = 1. The initial values ​​are α1 = 0.3, α2 = 0.3, α3 = 0.2, and α4 = 0.2. Machine efficiency reflects the continuous stability of the production process and, combined with the AA rate, directly reflects the stability of process parameters during production. Winder efficiency = (winder operation time / winder planned operation time) * 100%. Equipment failure rate is a direct and important indicator of equipment stability and maintenance efficiency. The more stable the process and equipment parameters, or the more closely they match production, the lower the failure rate. Equipment failure rate = (equipment downtime / (24 * 60 * actual number of days in the calendar month)) * 100%.

[0125] When the loss value is greater than the set value, the model parameters are adjusted and new samples are input into the multi-layer neural network. This process is iterated until the loss value is less than the set value, and the quality feedback model is obtained.

[0126] In the embodiment of the present disclosure, the input features of the input layer may include quality inspection results and production parameters input into the neural network, and the output features of the output layer may include predicted process parameters.

[0127] In the embodiment of the present disclosure, the sample set may include one or more of a training set, a test set, and a validation set. The samples in the sample set may be obtained from historical data of the knowledge graph.

[0128] According to the embodiment of the present disclosure, the quality feedback model obtained by training based on historical data can make the detection results using the quality feedback model more accurate.

[0129] Figure 8 is a schematic diagram of a portion of a knowledge graph according to an embodiment of the present disclosure. Figure 8As shown, this portion of the knowledge graph includes the equipment knowledge framework, spare parts knowledge framework, inventory knowledge framework, procurement knowledge framework, process parameter knowledge framework, maintenance record knowledge framework, quality inspection result knowledge framework, and tool status knowledge framework. Within this knowledge graph, the equipment knowledge framework is associated with the spare parts knowledge framework, which is in turn associated with the inventory knowledge framework, which is then associated with the procurement knowledge framework. The equipment knowledge framework is also associated with the process parameter knowledge framework, which is in turn associated with the maintenance record knowledge framework, which is then associated with the tool status knowledge framework. The process parameter knowledge framework is also associated with the quality inspection result knowledge framework. This portion of the knowledge graph allows for the construction of a knowledge linkage system between products, equipment, and processes.

[0130] Figure 9 The figure is a schematic diagram of the device knowledge framework in an embodiment of the present disclosure. The device knowledge framework may include a device name slot, a line slot, and a machine number slot. The device name slot is used to store the device name, such as reactor, spinning manifold, winder, etc. The line slot can be used to store the channel and production line where the device is located, such as "WDC 1" and "WDC 2." The machine number slot can be used to store the location of the device on the production line, such as 01, 02, 12, 24, etc. Figure 10 It is a schematic diagram of the process parameter knowledge framework in the embodiment of the present disclosure. The knowledge framework may include a spinning speed slot, a fineness center value slot, a tension slot, a hot roller temperature slot, etc. Among them, the spinning speed slot can be used to store the winding speed of the winding machine, such as the spinning speed range corresponding to the pre-oriented yarn (PRE-ORIENTED YARN OR PARTIALLYORIENTED YARNDTY, POY) can be "2710M / min-2715M / min", "2700M / min-2705M / min", and the spinning speed range corresponding to the full-drawn yarn (FULL DRAW YARN, FDY) can be "4100M / min-4105M / min", "4400M / min-4405M / min" or "4600M / min-4605M / min". The fineness center value slot can be used to store the thick line of the yarn, such as "167±2.5%", "261±2.5%". The tension slot can be used to store the magnitude of the tension applied to the wire, such as "10 cN", "14 cN", or "18 cN". The hot roller temperature can be used to store the temperature of the hot roller, such as "92-96°C", or "141°C-145°C".

[0131] The knowledge graph can be used to correlate key equipment, spare parts, and spare parts inventory distribution. Combined with equipment failure maintenance records (detailed processing), in the event of an equipment failure, the problem can be quickly located and analyzed based on historical maintenance experience, and maintenance recommendations can be provided to guide maintenance personnel in performing repairs. Outbound delivery tasks are automatically generated based on spare parts inventory and the storage of proprietary tools. In the event of insufficient spare parts inventory, spare parts can be automatically transferred from other warehouses. In the event that spare parts inventory falls below safety stock, procurement tasks can be automatically generated to guide procurement personnel in making purchases.

[0132] Through the knowledge graph, you can also query the knowledge graph to obtain abnormal upstream process parameters (such as abnormal temperature, viscosity, motor current, voltage, etc. of a certain reactor) based on product inspection results (such as abnormal non-dye color judgment results, abnormal external inspection / chemical inspection results, etc.), and query the normal range corresponding to the abnormal parameter name in the knowledge graph based on the abnormal parameter name, and give parameter adjustment suggestions based on the normal range.

[0133] Through the knowledge graph, it is also possible to provide process parameter optimization suggestions for the production of subsequent products based on the normal production results of the product and the corresponding historical data of the equipment / process during the normal production process, thereby further optimizing production efficiency and product quality.

[0134] During the production process, if abnormalities occur in the equipment or process parameters of a certain link, an early warning can be issued, and the relevant personnel can be notified to track and handle emergencies in a timely manner. Adjustment suggestions can also be given for the upstream and downstream related equipment and process parameters to ensure the yield rate of the product.

[0135] Figure 11 : is a schematic structural diagram of a silk ingot quality control device based on a knowledge graph according to an embodiment of the present disclosure, the device comprising:

[0136] A determination module 1101 is configured to determine whether there are abnormal parameters in the production parameters and / or process parameters of a group of silk ingots based on the quality inspection results, production parameters, and process parameters of the group of silk ingots;

[0137] A search module 1102 is configured to search, in the case where the abnormal parameter exists, for an adjustment method corresponding to the production parameter and / or the process parameter in the ingot production management knowledge graph;

[0138] The sending module 1103 is configured to send the production parameters and / or the adjustment method corresponding to the process parameters to the related equipment of the group of ingots.

[0139] Figure 121 is a schematic diagram of the structure of a knowledge graph-based ingot quality control device according to an embodiment of the present disclosure. The device may include one or more features of the knowledge graph-based ingot quality control device described above. In one embodiment, the group of ingots includes a group of ingots with the same batch number, and the determination module 1101 includes:

[0140] A determination submodule 1201 is configured to determine, if the quality inspection result is abnormal, whether the production parameters and / or process parameters of the group of ingots are within a normal range based on the ingot production management knowledge graph;

[0141] The acquisition submodule 1202 is configured to acquire abnormal parameters that are not within a normal range from the process parameters of the group of ingots.

[0142] In one embodiment, Figure 12 As shown, the device also includes:

[0143] The saving module 1203 is configured to save the quality inspection results, the production parameters, and the process parameters of the group of ingots into the ingot production management knowledge graph if the quality inspection results are normal.

[0144] In one embodiment, the production parameters include at least one of the following: line type, machine number, specification, batch number, drop number, and doffing time; the quality inspection results include at least one of the following: undyed color judgment spectrum information, undyed color judgment abnormality results, appearance inspection results, and physical and mechanical property inspection results; the process parameters include at least one of the following: tension, spinning speed, oil content, oil model, oil application rate, hot roller temperature, fineness center value, metering pump specification, metering pump speed, spinneret diameter, spinneret aspect ratio, full barrel weight, and network pressure.

[0145] In one embodiment, Figure 12 As shown, the search module 1102 includes:

[0146] The first search submodule 1204 is configured to search the ingot production management knowledge graph for normal process parameters corresponding to the abnormal parameters, and determine a process adjustment method based on the normal process parameters;

[0147] The second search submodule 1205 is configured to search the ingot production management knowledge graph for device information corresponding to the abnormal parameter, and determine a device adjustment method based on the device information.

[0148] In one embodiment, the equipment information corresponding to the abnormal parameter includes at least one of the following: equipment and / or components that require maintenance; upstream and downstream associated equipment and / or components of the equipment and / or components that require maintenance; maintenance records of equipment and / or components that require maintenance; storage information of spare equipment and / or spare parts; and procurement information of spare equipment and / or spare parts.

[0149] In one embodiment, the second search submodule 1205 is further configured to initiate a maintenance task based on the device information corresponding to the abnormal parameter. The maintenance task includes at least one of the following:

[0150] Determine, based on the maintenance records of the equipment and / or component requiring maintenance, a maintenance method corresponding to the equipment and / or component requiring maintenance; and initiate, based on the maintenance method, a maintenance task for the faulty equipment and / or faulty component to a maintenance management device, the maintenance task including an identification of the faulty equipment and / or faulty component;

[0151] When the local inventory of spare equipment and / or spare parts falls below a safety threshold, a procurement task for the spare equipment and / or spare parts is initiated to the procurement management system, where the procurement task includes procurement information of the equipment and / or spare parts to be purchased;

[0152] When the local inventory of spare equipment and / or spare parts falls below a safety threshold, the system searches for the spare equipment and / or spare parts in the off-site inventory. If so, it initiates a transfer task to the off-site warehouse management device, which includes the inventory information of the equipment and / or spare parts to be transferred.

[0153] When the local and remote inventories of spare equipment and / or spare parts are both below the safety threshold, an emergency processing task is initiated, which includes an emergency procurement task and / or an idle equipment borrowing task.

[0154] In one embodiment, Figure 12 As shown, the device also includes:

[0155] A construction module 1206 is configured to construct one or more ingot production management knowledge frameworks and establish associations between the one or more ingot production management knowledge frameworks; wherein the ingot production management knowledge framework includes one or more slots;

[0156] An acquisition module 1207 is used to obtain ingot production management knowledge data based on the single ingot data flow system, the quality feedback model, the maintenance record, and the storage data;

[0157] The fusion module 1208 is used to fuse the ingot production management knowledge data, set the fused ingot production management knowledge data as the slot value of the one or more slots in the one or more ingot production management knowledge frameworks, and obtain the ingot production management knowledge graph.

[0158] In one embodiment, the one or more ingot production management knowledge frameworks include a production parameter knowledge framework, an inspection result knowledge framework, a process parameter knowledge framework, an equipment information knowledge framework, an equipment maintenance record framework, and associations between the various knowledge frameworks;

[0159] Among them, the production parameter knowledge framework includes specification slot, batch number slot, drop slot, and drop time slot; the inspection result knowledge framework includes dye-free color judgment spectrum information slot, dye-free color judgment abnormality result slot, external detection result slot, and physical and mechanical property detection result slot; the process parameter knowledge framework includes tension slot, spinning speed slot, oil content slot, oil model slot, oil application rate slot, hot roller temperature slot, fineness center value slot, metering pump specification slot, metering pump speed slot, spinneret diameter slot, spinneret aspect ratio slot, full barrel weight slot, and network pressure slot; the equipment information knowledge framework includes line identification slot, machine number slot, equipment name slot, equipment type slot, storage information slot, spare parts slot, and maintenance record slot; the equipment maintenance record knowledge framework includes equipment name slot, equipment position number slot, fault / alarm information slot, and maintenance information slot.

[0160] The ingot production management knowledge data includes at least one of production parameter data, quality inspection result data, process parameter data, and equipment information data.

[0161] In one embodiment, Figure 12 As shown, the device also includes:

[0162] The input module 1209 is used to input the quality inspection results, the production parameters and the process parameters of the multi-spindle silk ingot into the quality feedback model to obtain the product status of the multi-spindle silk ingot.

[0163] In one embodiment, the product status includes at least one of a yield rate, a full roll rate, and a broken end rate.

[0164] In one embodiment, Figure 12 As shown, the device also includes:

[0165] The trigger module 1210 is used to trigger the execution based on the quality inspection results, production parameters and process parameters of a group of silk ingots when the product status of the multiple silk ingots output by the quality feedback model meets the qualified threshold, and determine whether there are abnormal parameters in the production parameters and / or process parameters of the group of silk ingots.

[0166] In one embodiment, the training process of the quality feedback model includes:

[0167] Inputting the quality inspection results, production parameters, and process parameters of the ingot training samples in the sample set into a first model composed of a multi-layer neural network, and outputting a predicted product state;

[0168] Iteratively training the first model based on the labeled product status of the ingot training sample and the loss function constructed by the predicted product status to obtain a second model;

[0169] The sample set includes a plurality of silk ingot training samples obtained from the silk ingot production management knowledge graph, and each of the plurality of silk ingot training samples includes the mutually related quality inspection results, production parameters, and process parameters;

[0170] The second model is the trained quality feedback model.

[0171] In one embodiment, the related equipment includes at least one of the following: production equipment; terminal equipment; control equipment.

[0172] For the description of specific functions and examples of each module and submodule of the device in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the above method embodiment, which will not be repeated here.

[0173] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0174] Figure 13 FIG. 1 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Figure 13 As shown, the electronic device includes: a memory 1310 and a processor 1320. The memory 1310 stores a computer program that can be executed on the processor 1320. The number of memory 1310 and processor 1320 can be one or more. The memory 1310 can store one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device performs the method provided by the above method embodiment. The electronic device may also include: a communication interface 1330 for communicating with external devices and performing data exchange.

[0175] If the memory 1310, the processor 1320, and the communication interface 1330 are implemented independently, the memory 1310, the processor 1320, and the communication interface 1330 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 13 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0176] Optionally, in a specific implementation, if the memory 1310, the processor 1320 and the communication interface 1330 are integrated on a chip, the memory 1310, the processor 1320 and the communication interface 1330 can communicate with each other through an internal interface.

[0177] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0178] Furthermore, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DR RAM).

[0179] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, data subscriber line (DSL)) or wireless (e.g., infrared, Bluetooth, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, or a magnetic tape), an optical medium (e.g., a digital versatile disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)). It is worth noting that the computer-readable storage medium mentioned in the present disclosure may be a non-volatile storage medium, in other words, a non-transient storage medium.

[0180] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0181] In the description of the embodiments of the present disclosure, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0182] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means or. For example, A / B can mean A or B. "And / or" in this document is only a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0183] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0184] The above description is merely an exemplary embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure shall be included in the scope of protection of the present disclosure.

Claims

1. A method for controlling ingot quality based on a knowledge graph, comprising: determining whether there are abnormal parameters in the production parameters and / or the process parameters of the group of silk ingots based on quality inspection results, production parameters and process parameters of the group of silk ingots; In the case where the abnormal parameters exist, searching for adjustment methods corresponding to the production parameters and / or the process parameters in the ingot production management knowledge map; Sending the production parameters and / or the adjustment methods corresponding to the process parameters to relevant equipment of the group of ingots; The group of silk ingots includes a group of silk ingots of the same batch number; based on the quality inspection results, production parameters, and process parameters of the group of silk ingots, determining whether there are abnormal parameters in the production parameters and / or the process parameters of the group of silk ingots, including: if the quality inspection results are abnormal, determining whether the production parameters and / or the process parameters of the group of silk ingots are within a normal range based on the silk ingot production management knowledge graph; and obtaining abnormal parameters that are not within the normal range from the production parameters and / or the process parameters of the group of silk ingots; Among them, in the case where the abnormal parameters exist, the adjustment method corresponding to the production parameters and / or the process parameters is searched in the silk ingot production management knowledge graph, including: searching for normal process parameters corresponding to the abnormal parameters in the silk ingot production management knowledge graph, and determining the process adjustment method based on the normal process parameters; searching for equipment information corresponding to the abnormal parameters in the silk ingot production management knowledge graph, and determining the equipment adjustment method based on the equipment information.

2. The method according to claim 1, further comprising: When the quality inspection result is normal, the quality inspection result, the production parameters and the process parameters of the group of silk ingots are saved in a silk ingot production management knowledge graph.

3. The method according to claim 1 or 2, wherein the production parameters include at least one of the following: line type, machine number, specification, batch number, drop order, and doffing time; the quality inspection results include at least one of the following: dye-free color spectrum information, dye-free color abnormality results, appearance inspection results, and physical and mechanical property inspection results; the process parameters include at least one of the following: tension, spinning speed, oil content, oil type, oil application rate, hot roller temperature, fineness center value, metering pump specification, metering pump speed, spinneret diameter, spinneret aspect ratio, full barrel weight, and network pressure.

4. The method according to claim 1, wherein Determining a device adjustment method based on the device information includes: Initiating a maintenance task based on the device information corresponding to the abnormal parameter, the maintenance task including at least one of the following: Determining, based on the maintenance records of the equipment and / or components requiring maintenance, a maintenance method corresponding to the equipment and / or components requiring maintenance; initiating, based on the maintenance method, a maintenance task for the faulty equipment and / or faulty components to a maintenance management device, the maintenance task including an identification of the faulty equipment and / or faulty components; Initiating a procurement task for the spare equipment and / or spare parts to a procurement management system when the local inventory of the spare equipment and / or spare parts is below a safety threshold, wherein the procurement task includes procurement information of the spare equipment and / or spare parts; When the local inventory of spare equipment and / or spare parts falls below a safety threshold, a search is performed to determine whether the spare equipment and / or spare parts are available in the off-site inventory; if so, a transfer task is initiated to the off-site warehouse management device, the transfer task including the inventory information of the equipment and / or spare parts to be transferred; When the local and remote inventories of spare equipment and / or spare parts are both below a safety threshold, an emergency processing task is initiated, which includes an emergency procurement task and / or an idle equipment loan task.

5. The method according to claim 1 or 2, wherein: The equipment information corresponding to the abnormal parameters includes at least one of the following: equipment and / or components that require maintenance; upstream and downstream associated equipment and / or components of the equipment and / or components that require maintenance; maintenance records of equipment and / or components that require maintenance; storage information of spare equipment and / or spare parts; and procurement information of spare equipment and / or spare parts.

6. The method according to claim 1 or 2, further comprising: Constructing one or more ingot production management knowledge frameworks, and establishing associations between the one or more ingot production management knowledge frameworks; wherein the ingot production management knowledge frameworks include one or more slots; Based on the single spindle data flow system, anomaly detection model, quality feedback model, maintenance records and storage data, the silk spindle production management knowledge data is obtained; The ingot production management knowledge data is integrated, and the integrated ingot production management knowledge data is set as the slot value of the one or more slots in the one or more ingot production management knowledge frameworks to obtain the ingot production management knowledge graph.

7. The method according to claim 6, wherein: The one or more ingot production management knowledge frameworks include a production parameter knowledge framework, an inspection result knowledge framework, a process parameter knowledge framework, an equipment information knowledge framework, an equipment maintenance record knowledge framework, and associations between the various knowledge frameworks; Among them, the production parameter knowledge framework includes a specification slot, a batch number slot, a drop slot, and a drop time slot; the inspection result knowledge framework includes a non-dye color judgment spectrum information slot, a non-dye color judgment abnormality result slot, an external detection result slot, and a physical and mechanical property detection result slot; the process parameter knowledge framework includes a tension slot, a spinning speed slot, an oil content slot, an oil model slot, an oil application rate slot, a hot roller temperature slot, a fineness center value slot, a metering pump specification slot, a metering pump speed slot, a spinneret diameter slot, a spinneret aspect ratio slot, a full barrel weight slot, and a network pressure slot; the equipment information knowledge framework includes a line identification slot, a machine number slot, an equipment name slot, an equipment type slot, a storage information slot, a spare parts slot, and a maintenance record slot; the equipment maintenance record knowledge framework includes an equipment name slot, an equipment position number slot, a fault / alarm information slot, and a maintenance information slot; The ingot production management knowledge data includes at least one of production parameter data, quality inspection result data, process parameter data, and equipment information data.

8. The method according to claim 1, further comprising: The quality inspection results, the production parameters and the process parameters of the multi-spindle silk ingot are input into a quality feedback model to obtain the product status of the multi-spindle silk ingot.

9. The method according to claim 8, wherein The product status includes at least one of a yield rate, a full roll rate, and a broken end rate.

10. The method according to claim 8 or 9, further comprising: When the product status of the multiple silk ingots output by the quality feedback model meets the qualified threshold, it triggers execution based on the quality inspection results, production parameters and process parameters of a group of silk ingots to determine whether there are abnormal parameters in the production parameters and / or process parameters of the group of silk ingots.

11. The method according to claim 8, wherein the training process of the quality feedback model comprises: Inputting the quality inspection results, production parameters, and process parameters of the ingot training samples in the sample set into a first model composed of a multi-layer neural network, and outputting a predicted product state; Iteratively training the first model based on the labeled product status of the ingot training sample and the loss function constructed by the predicted product status to obtain a second model; The sample set includes a plurality of silk ingot training samples obtained from the silk ingot production management knowledge graph, and each of the plurality of silk ingot training samples includes the mutually related quality inspection results, production parameters, and process parameters; The second model is the trained quality feedback model.

12. A silk ingot quality control device based on a knowledge graph, comprising: a determination module, configured to determine whether there are abnormal parameters in the production parameters and / or the process parameters of the group of silk ingots based on quality inspection results, production parameters and process parameters of the group of silk ingots; a search module, configured to search, in the case where the abnormal parameters exist, for an adjustment method corresponding to the production parameters and / or the process parameters in the ingot production management knowledge graph; a sending module, configured to send the production parameters and / or the adjustment methods corresponding to the process parameters to relevant equipment of the group of ingots; The group of silk ingots includes a group of silk ingots of the same batch number, and the determination module includes: a determination submodule for determining, if an abnormality is found in the quality inspection result, whether the production parameters and / or the process parameters of the group of silk ingots are within a normal range based on the silk ingot production management knowledge graph; and an acquisition submodule for acquiring abnormal parameters that are not within the normal range from the production parameters and / or the process parameters of the group of silk ingots; Among them, the search module includes: a first search sub-module, which is used to search for normal process parameters corresponding to the abnormal parameters in the silk ingot production management knowledge graph, and determine the process adjustment method based on the normal process parameters; a second search sub-module, which searches for equipment information corresponding to the abnormal parameters in the silk ingot production management knowledge graph, and determines the faulty equipment and the corresponding adjustment method based on the equipment information and the adjustment method.

13. The apparatus according to claim 12, further comprising: A saving module is used to save the quality inspection results, the production parameters and the process parameters of the group of silk ingots into the silk ingot production management knowledge graph when the quality inspection results are normal.

14. The device according to claim 12 or 13, wherein the production parameters include at least one of the following: line type, machine number, specification, batch number, drop order, and doffing time; the quality inspection results include at least one of the following: undyed color judgment spectrum information, undyed color judgment abnormality results, external detection results, and physical and mechanical property detection results; the process parameters include at least one of the following: tension, spinning speed, oil content, oil model, oil application rate, hot roller temperature, fineness center value, metering pump specification, metering pump speed, spinneret diameter, spinneret aspect ratio, full barrel weight, and network pressure.

15. The device according to claim 12, wherein The second search submodule is further configured to initiate a maintenance task based on the device information corresponding to the abnormal parameter, wherein the maintenance task includes at least one of the following: Determining, based on the maintenance records of the equipment and / or components requiring maintenance, a maintenance method corresponding to the equipment and / or components requiring maintenance; initiating, based on the maintenance method, a maintenance task for the faulty equipment and / or faulty components to a maintenance management device, the maintenance task including an identification of the faulty equipment and / or faulty components; Initiating a procurement task for the spare equipment and / or spare parts to a procurement management system when the local inventory of the spare equipment and / or spare parts is below a safety threshold, wherein the procurement task includes procurement information of the spare equipment and / or spare parts; When the local inventory of spare equipment and / or spare parts falls below a safety threshold, a search is performed to determine whether the spare equipment and / or spare parts are available in the off-site inventory; if so, a transfer task is initiated to the off-site warehouse management device, the transfer task including the inventory information of the equipment and / or spare parts to be transferred; When the local and remote inventories of spare equipment and / or spare parts are both below a safety threshold, an emergency processing task is initiated, which includes an emergency procurement task and / or an idle equipment loan task.

16. The device according to claim 12 or 13, wherein The equipment information corresponding to the abnormal parameters includes at least one of the following: equipment and / or components that require maintenance; upstream and downstream associated equipment and / or components of the equipment and / or components that require maintenance; maintenance records of equipment and / or components that require maintenance; storage information of spare equipment and / or spare parts; and procurement information of spare equipment and / or spare parts.

17. The apparatus according to claim 12 or 13, further comprising: A construction module, configured to construct one or more ingot production management knowledge frameworks and establish association relationships between the one or more ingot production management knowledge frameworks; wherein the ingot production management knowledge frameworks include one or more slots; The acquisition module is used to obtain the silk ingot production management knowledge data based on the single ingot data flow system, quality feedback model, maintenance records and storage data; A fusion module is used to fuse the silk ingot production management knowledge data, set the fused silk ingot production management knowledge data as the slot value of the one or more slots in the one or more silk ingot production management knowledge frameworks, and obtain the silk ingot production management knowledge graph.

18. The device according to claim 17, wherein The one or more ingot production management knowledge frameworks include a production parameter knowledge framework, an inspection result knowledge framework, a process parameter knowledge framework, an equipment information knowledge framework, an equipment maintenance record knowledge framework, and associations between the various knowledge frameworks; Among them, the production parameter knowledge framework includes a specification slot, a batch number slot, a drop slot, and a drop time slot; the inspection result knowledge framework includes a non-dye color judgment spectrum information slot, a non-dye color judgment abnormality result slot, an external detection result slot, and a physical and mechanical property detection result slot; the process parameter knowledge framework includes a tension slot, a spinning speed slot, an oil content slot, an oil model slot, an oil application rate slot, a hot roller temperature slot, a fineness center value slot, a metering pump specification slot, a metering pump speed slot, a spinneret diameter slot, a spinneret aspect ratio slot, a full barrel weight slot, and a network pressure slot; the equipment information knowledge framework includes a line identification slot, a machine number slot, an equipment name slot, an equipment type slot, a storage information slot, a spare parts slot, and a maintenance record slot; the equipment maintenance record knowledge framework includes an equipment name slot, an equipment position number slot, a fault / alarm information slot, and a maintenance information slot; The ingot production management knowledge data includes at least one of production parameter data, quality inspection result data, process parameter data, and equipment information data.

19. The apparatus according to claim 12, further comprising: An input module is used to input the quality inspection results, the production parameters and the process parameters of the multi-spindle silk ingot into a quality feedback model to obtain the product status of the multi-spindle silk ingot.

20. The device according to claim 19, wherein The product status includes at least one of a yield rate, a full roll rate, and a broken end rate.

21. The apparatus according to claim 19 or 20, further comprising: A trigger module is used to trigger the execution based on the quality inspection results, production parameters and process parameters of a group of silk ingots when the product status of the multiple silk ingots output by the quality feedback model meets the qualified threshold, and determine whether there are abnormal parameters in the production parameters and / or process parameters of the group of silk ingots.

22. The apparatus according to claim 19, wherein the training process of the quality feedback model comprises: Inputting the quality inspection results, production parameters, and process parameters of the ingot training samples in the sample set into a first model composed of a multi-layer neural network, and outputting a predicted product state; Iteratively training the first model based on the labeled product status of the ingot training sample and the loss function constructed by the predicted product status to obtain a second model; The sample set includes a plurality of silk ingot training samples obtained from the silk ingot production management knowledge graph, and each of the plurality of silk ingot training samples includes the mutually related quality inspection results, production parameters, and process parameters; The second model is the trained quality feedback model.

23. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

Images