Fault detection method and device for die-casting machine, control equipment and readable storage medium

Abstract

The invention is suitable for the technical field of computers, and provides a fault detection method and device for a die-casting machine, control equipment and a computer readable storage medium, and the method comprises the steps: obtaining the real-time operation state data of the die-casting machine in the production process; detecting the running state data in real time through a local fault detection service to obtain a local detection result; performing fault detection on the operation state data through remote fault detection service to obtain a remote detection result; updating a local fault detection service based on the difference between the local detection result and the remote detection result; and detecting the operation state data based on the updated local fault detection service to obtain a target detection result of the operation state data. The fault detection accuracy of the die-casting machine is improved based on a dual fault detection and updating mechanism.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to a fault detection method, device, control equipment and computer-readable storage medium for a die-casting machine. Background Art

[0002] The die-casting machine is a complex integrated system involving multiple subsystems such as electrical, mechanical and hydraulic systems. They are highly coupled and mutually influential, and there are multiple sources of uncertainty. With the complexity of the die-casting machine control system and multi-closed-loop automated production, the initial fault phenomenon is more hidden, and if it is not identified, it will continue to deteriorate, often leading to unplanned shutdowns, and the product quality during this period cannot be guaranteed. The traditional solution is to perform equipment maintenance regularly, but maintenance is often excessive or untimely, which cannot reduce production line shutdowns and production losses.

[0003] The existing die-casting machine fault detection system mainly relies on the fault judgment logic preset by the equipment at the factory to detect the current status information, which makes it difficult to identify the comprehensive fault phenomenon. The inherent relationship between the fault phenomenon and multi-source information cannot be identified, resulting in unclear fault location. At the same time, relevant fault experience cannot be accumulated, the ability of the operation and maintenance system users is high, and the fault diagnosis function solidified locally is difficult to update. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a fault detection method, apparatus, control device and computer-readable storage medium for a die-casting machine, which can improve the fault detection accuracy of the die-casting machine through a dual fault detection and update mechanism.

[0005] A first aspect of an embodiment of the present application provides a fault detection method for a die casting machine, comprising:

[0006] Obtain the operating status data of the die-casting machine during the production process;

[0007] By using a local fault detection service, the operating status data is detected in real time to obtain a local detection result;

[0008] Through the remote fault detection service, remote fault detection is performed on the operating status data to obtain a remote detection result;

[0009] Based on the difference between the local detection result and the remote detection result, updating the local fault detection service;

[0010] Based on the updated local fault detection service, the running status data is detected to obtain a target detection result of the running status data.

[0011] In an implementation of the first aspect, the real-time detection of the operation status data through the local fault detection service to obtain a local detection result includes:

[0012] Based on the preset feature recognition points of the local fault detection service, the operation status data is detected in real time to obtain a first fault phenomenon;

[0013] From the local knowledge base, retrieve a first fault model adapted to the first fault phenomenon, where the first fault model is used to store at least one fault cause that triggers the first fault phenomenon and the inspection operations associated with each fault cause;

[0014] Based on the first fault phenomenon and the first fault model, determine the local detection result.

[0015] In an implementation of the first aspect, the local fault detection service includes multiple diagnostic units, and each diagnostic unit includes at least one feature recognition point.

[0016] The real-time detection of the operation status data through the local fault detection service to obtain a local detection result includes:

[0017] Based on each diagnostic unit, perform parallel diagnostic processing on the operation status data respectively to obtain the specified feature recognition points matched by the operation status data;

[0018] Based on each of the specified feature recognition points, match with the fault models in the local knowledge base to obtain the specified fault models that the operation status data conforms to;

[0019] Determine the fault phenomenon of the specified fault model as the first fault phenomenon associated with the operation status data;

[0020] Based on the first fault phenomenon and the first fault model, determine the local detection result.

[0021] In an implementation of the first aspect, the multiple diagnostic units include: a numerical control diagnostic unit, a mechanical diagnostic unit, a hydraulic diagnostic unit, and an electrical diagnostic unit;

[0022] Among them, the numerical control diagnostic unit is used to detect the equipment power components and numerical control components;

[0023] The mechanical diagnostic unit is used to inspect mechanical components and actions;

[0024] The hydraulic diagnostic unit is used to detect hydraulic components and actions;

[0025] The electrical diagnostic unit is used to detect electrical components and control systems.

[0026] In an implementation of the first aspect, based on the preset feature recognition points of each diagnostic unit of the local fault detection service, determine the first fault phenomenon associated with the operating status data; including:

[0027] Based on each of the diagnostic units, perform parallel diagnostic processing on the operating status data to determine the target feature recognition points corresponding to the operating status data;

[0028] According to the target feature recognition points, match with the fault models in the local knowledge base to find the specified fault model that the operating status data conforms to;

[0029] Determine the fault phenomenon of the specified fault model as the first fault phenomenon associated with the operating status data.

[0030] In an implementation of the first aspect, the remote fault detection of the operating status data through the remote fault detection service to obtain a remote detection result includes:

[0031] Through the remote fault detection service, combine the cloud inference engine and the remote knowledge base to perform real-time inference analysis on the operating status data to determine the second fault phenomenon that the operating status data conforms to;

[0032] Retrieve from the remote knowledge base the second fault model adapted to the second fault phenomenon, where the remote knowledge base is used to store the fault phenomena associated with various different types of die-casting machines and the fault models of the fault phenomena;

[0033] Based on the second fault phenomenon and the second fault model, determine the remote detection result.

[0034] In an implementation of the first aspect, the updating of the local fault detection service based on the difference between the local detection result and the remote detection result includes:

[0035] Perform a difference analysis on the first fault model of the first fault phenomenon of the local detection result and the second fault model of the second fault phenomenon of the remote detection result;

[0036] Based on the analysis result, determine the potential fault model, and determine the potential diagnostic unit and potential feature recognition points corresponding to the potential fault model;

[0037] Based on the potential fault model, the potential diagnostic unit, and the potential feature recognition points, update the local fault detection service.

[0038] In an implementation of the first aspect, the detection of the operating status data based on the updated local fault detection service to obtain the target detection result of the operating status data includes:

[0039] Based on the updated local fault detection service, determine the target fault phenomenon of the operation status data;

[0040] Determine the fault weight of each fault cause in the target fault model corresponding to the target fault phenomenon for the target fault phenomenon;

[0041] According to each of the fault weights, sort each fault cause in the target fault model to obtain the target detection result of the operation status data.

[0042] The second aspect of the embodiments of the present application provides a fault detection device for a die-casting machine, including:

[0043] An acquisition module, configured to acquire real-time operation status data of the die-casting machine during the production process;

[0044] A local detection module, configured to perform real-time detection on the operation status data through a local fault detection service to obtain a local detection result;

[0045] A remote detection module, configured to perform remote fault detection on the operation status data through a remote fault detection service to obtain a remote detection result;

[0046] An update module, configured to update the local fault detection service based on the difference between the local detection result and the remote detection result;

[0047] A target detection module, configured to perform detection on the operation status data based on the updated local fault detection service to obtain a target detection result for the operation status data.

[0048] The third aspect of the embodiments of the present application provides a control device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect above is implemented.

[0049] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0050] In the first aspect of the embodiments of the present application, by first obtaining in real time the key operation status data of the die-casting machine during the die-casting process, it is possible to ensure the timely detection of abnormal situations. Then, the local fault detection service is used for quick response to achieve preliminary fault identification and improve the fault response speed. Next, combined with the professional analysis ability of the remote fault detection service, the fault diagnosis result is further verified and refined to improve the accuracy. Finally, the local detection result is supplemented and corrected by the remote detection result to ensure that the fault detection result is more comprehensive and reliable. In this way, through the dual fault detection and update mechanism, the fault detection accuracy of the die-casting machine is improved.

[0051] It can be understood that for the beneficial effects of the above second aspect to the fourth aspect, reference can be made to the relevant descriptions in the above first aspect, and details are not described herein again. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a schematic flowchart of the implementation of the fault detection method for the die-casting machine provided by the embodiments of the present application;

[0054] Figure 2 It is a schematic structural diagram of the fault model provided by the embodiments of the present application;

[0055] Figure 3 It is a schematic structural diagram of the fault detection system for the die-casting machine provided by the embodiments of the present application;

[0056] Figure 4 It is a schematic flowchart of the implementation of the local fault detection method provided by the embodiments of the present application;

[0057] Figure 5 It is a schematic flowchart of the implementation of the method for determining the first fault phenomenon provided by the embodiments of the present application;

[0058] Figure 6 It is an example diagram of the operation status data provided by the embodiments of the present application;

[0059] Figure 7 It is an example diagram of the visualization processing of the operation status data provided by the embodiments of the present application;

[0060] Figure 8 It is an example diagram of the fault model with the fault phenomenon of the hammer head getting stuck provided by the embodiments of the present application;

[0061] Figure 9It is a schematic flow chart of the implementation of the remote fault detection method provided by the embodiments of the present application;

[0062] Figure 10 It is a schematic flow chart of the update method of the local fault detection service provided by the embodiments of the present application;

[0063] Figure 11 It is a schematic diagram of the fault detection device of the die-casting machine provided by the embodiments of the present application;

[0064] Figure 12 It is a schematic diagram of the control device provided by the embodiments of the present application. Detailed implementation manners

[0065] In one embodiment, as Figure 1 shown, a fault detection method for a die-casting machine is provided. This method is applied to a control device connected to the die-casting machine and includes the following steps S101 to S105:

[0066] Step S101, obtain the real-time operation status data of the die-casting machine during production.

[0067] In application, the operation status data are the operation parameters of each component (mechanism) of the die-casting machine during production, which can reflect the actual working condition of the die-casting machine. The control device continuously collects the operation status data of the die-casting machine during the die-casting process through various sensors (such as temperature sensors, pressure sensors, position sensors, liquid level sensors, etc.) installed on the die-casting machine or through communication with the device. The operation status data are stored in a storage space (such as a database, a file system, etc.) in a preset format.

[0068] Step S102, perform real-time detection on the operation status data through the local fault detection service to obtain a local detection result.

[0069] In application, due to the characteristics of strong concealment and high coupling degree of die-casting system faults, the collected data have problems such as a large number of samples, diverse fault modes, high dimensions, and high redundancy, which seriously restrict the data analysis ability of the fault diagnosis model. To address the above problems, multiple diagnostic units are used to process different types of faults in parallel. While reducing the model complexity, the advantages of different algorithms can be effectively utilized for targeted diagnosis, achieving complementary advantages.

[0070] The local fault detection service is a fault detection system based on a locally deployed die-casting machine, which is divided into three major parts: a diagnosis system, a local knowledge base, and a human-machine interaction interface. The diagnosis system is further divided into a numerical control diagnosis unit, a mechanical diagnosis unit, a hydraulic diagnosis unit, and an electrical diagnosis unit. Among them, the numerical control diagnosis unit is used to detect the power components and numerical control components of the equipment; the mechanical diagnosis unit is used to check mechanical parts and actions; the hydraulic diagnosis unit is used to detect hydraulic parts and actions; the electrical diagnosis unit is used to detect electrical parts and control systems. Each diagnosis unit corresponds to at least one feature recognition point, and different diagnosis algorithms are adopted by each diagnosis unit to monitor the operation status data of the die-casting machine and generate feature recognition point data adapted to each diagnosis unit. When multiple feature recognition point data match the preset fault model, the corresponding fault phenomenon is confirmed to occur. The local inference engine analyzes the corresponding fault causes of the fault phenomenon and pops up the preset fault description, solution measures, etc. on the human-machine interface. The fault model is stored in the local knowledge base, and the schematic structure of a fault model is as Figure 2 shown. The fault model includes the fault causes of the corresponding fault phenomenon and the inspection operations used to repair each fault cause. The inspection operations are actually the solution measures for the fault causes.

[0071] In the application, the local detection results include the fault phenomenon and the fault model of the fault phenomenon. The fault detection results include the fault diagnosis results for the historical operation status data and the fault prediction results for the ongoing operation status data. Fault detection includes two aspects: fault diagnosis and fault prediction.

[0072] Step S103, perform fault detection on the operation status data through the remote fault detection service to obtain remote detection results.

[0073] In an application, to improve the comprehensiveness of fault detection and detect as many potential faults as possible, the control device can perform fault detection on the operation status data through a remote fault detection service. The remote fault detection service is an application program for remote fault detection of operation status data from multiple different sources based on a fault detection expert system of a die-casting machine deployed in the cloud. The remote fault detection service can detect more comprehensive fault phenomena of the die-casting machine and inspection operations for the fault phenomena than the local fault detection service. The remote platform is connected to multiple different types of die-casting machines. The expert system belongs to a method based on empirical knowledge and is applicable to control systems where it is not easy to establish a mechanism model. Its diagnosis is not necessarily completely based on quantitative data, but more on changes in non-quantitative features such as states, characteristics, and attributes. The monitoring method based on qualitative empirical knowledge requires a lot of complex and profound professional knowledge and long-term accumulated experience. The expert system is a computer software system that uses the knowledge of multiple experts in a certain field to solve difficult problems in that field. The remote fault detection service is deployed in the cloud and interacts with the control device and the local fault detection service through an Internet of Things (IoT) network module installed locally. The control device uploads the operation status data to the cloud storage space. The remote fault detection service performs reasoning and analysis on the operation status data through the cloud inference engine. Essentially, it performs multi-source analysis on multi-source information (operation status data from die-casting machines produced by different types and manufacturers) based on machine learning algorithms, updates the feature recognition points associated with the fault phenomena, improves the existing fault models and diagnostic unit logics, and stores the improved fault models, diagnostic unit logics, and remote diagnostic results in the cloud storage space (such as a cloud database, cloud file system). Based on the latest fault models and diagnostic units, the remote diagnostic results are sent to the local device. It should be noted that the remote knowledge base (also known as the cloud knowledge base) stores fault phenomena, fault models, fault diagnostic unit logics, etc., which is a general knowledge base for the faults of die-casting machines and includes the fault phenomena of various different types of die-casting machines. The remote detection results also belong to the fault detection results and include the fault phenomena and at least one fault cause for the fault phenomena.

[0074] In an application, a knowledge base (such as a local knowledge base, remote knowledge base, etc.) is a classified and organized collection of knowledge, including factual knowledge, empirical knowledge, principle knowledge, and control strategy knowledge, which is the manifestation of the knowledge of domain experts. An inference engine (local inference engine, cloud inference engine, etc.) includes the control strategies and problem-solving methods adopted by domain experts when solving problems. It uses the knowledge in the knowledge base for searching and reasoning, and finally obtains a problem-solving method.

[0075] Exemplarily, such as Figure 3Schematic diagram of the fault detection system structure of the die-casting machine shown. The fault detection system of the die-casting machine includes acquisition devices (such as numerical control systems, sensors, smart meters, etc.) deployed in various mechanisms of the die-casting machine for collecting operation status data, a controller for the die-casting machine to implement the fault detection method of the die-casting machine, a local fault detection service for local fault detection deployed by the local fault detection subsystem, and a remote fault detection service for remote fault detection deployed by the remote fault detection subsystem. The local fault detection subsystem includes a local knowledge base, a local diagnosis service, and a human-machine interaction interface. The remote fault detection subsystem includes a cloud knowledge base, a cloud inference engine, and a cloud human-machine interaction interface. By installing an IOT network module locally, the control device and the remote fault detection subsystem are connected. The fault detection system of the die-casting machine monitors the operation status data of the die-casting machine in real time. The operation status data is stored in the local storage space (such as a database, a file system, etc.). The local fault detection service analyzes the operation status data to generate feature recognition point data. When multiple feature recognition points match the fault model, the corresponding fault phenomenon is confirmed to occur. Fault detection includes fault diagnosis and fault warning. If it is fault diagnosis, the local diagnosis service outputs an alarm analysis of the fault. If it is fault prediction, the local diagnosis service outputs a warning of the fault and sends the local detection result to the human-machine interaction interface. The human-machine interaction interface outputs the fault detection result in a preset style. The preset style can be text, image, line graph, voice, etc.

[0076] In step S104, based on the difference between the local detection result and the remote detection result, the local fault detection service is updated.

[0077] In the application, in order to improve the comprehensiveness of fault detection and detect as many potential faults as possible, the control device performs remote fault detection on the operation status data by running the remote fault detection service. When the remote detection result is significantly different from the local detection result, an expert intervenes for evaluation and analysis to obtain an analysis result, and a new fault model called a potential fault model is generated according to the analysis result. The potential fault model is used to characterize the association relationship between the fault phenomenon and multi-source information. The potential fault model includes the fault causes that generate the fault phenomenon obtained by analyzing multi-source information, and the inspection operations used to repair each fault cause. The potential fault model and a new potential diagnosis unit adapted to the potential fault model can be sent from the cloud to the local machine. The potential fault model and the new potential diagnosis unit include potential fault phenomena not detected in the local fault detection result. In this way, by integrating the local and remote detection results, the fault cause can be more accurately located, providing a scientific basis for fault troubleshooting. The control device uses the remote detection result to update the local detection result to obtain the final fault detection result. The update process includes merging, deduplication, etc.

[0078] In an application, for the fault detection result of the operation status data, the control device can output the fault detection result through a preset output method. The preset output method can be to output the fault detection result through a human-machine interaction interface in a preset style (such as images, texts, statistical charts, etc.), or to remind the die-casting machine operator through a media information playback device (such as audio, video, etc.), or to directly store it in the storage space (database, file system, etc.) in a preset file format.

[0079] Step S105: Based on the updated local fault detection service, detect the operation status data to obtain the target detection result of the operation status data.

[0080] In this embodiment, first, by obtaining the key operation status data of the die-casting machine in the die-casting process in real time, it is possible to ensure that abnormal situations are discovered in a timely manner. Then, the local fault detection service is used for quick response to achieve preliminary fault identification and improve the fault response speed. Next, combined with the high computing power and strong algorithms of the remote fault detection service, the fault diagnosis result is further verified and refined to improve the accuracy. Finally, the local detection result is supplemented and corrected by the remote detection result to ensure that the fault detection result is more comprehensive and reliable. In this way, the fault detection accuracy of the die-casting machine is improved through a dual fault detection mechanism.

[0081] In one embodiment, as Figure 4 shown, the implementation process of step S102 includes the following steps S201 to S203:

[0082] Step S201: Based on the preset feature recognition points of the local fault detection service, identify faults in the operation status data to obtain the first fault phenomenon.

[0083] In an application, based on existing faults in the industry, multiple feature recognition points will be preset in advance. The fault detection conditions are composed of one or more feature recognition points and are used to judge the conditions required to belong to a specified fault phenomenon. The existence of a fault in the die-casting machine indicates that the actual value of at least one feature recognition point is different from the normal value (standard value) of this feature recognition point when the die-casting machine is operating normally. The local knowledge base associated with the local fault detection service includes at least one fault phenomenon and the fault model associated with each fault phenomenon. The control device analyzes the operation status data to judge whether it meets the preset fault detection conditions of a certain fault phenomenon. If it meets the specified fault detection conditions, the fault phenomenon corresponding to the specified fault detection conditions is used as the first fault phenomenon associated with the operation status data.

[0084] Exemplarily, taking the phenomenon of the hammer head jamming of a die-casting machine as an example, the preset fault detection conditions at least include the following feature recognition points: the speed is lower than the preset threshold, the feeding inlet pressure is greater than the pressure threshold, the feeding outlet pressure is less than the pressure threshold, etc. For any fault detection model, if the control device analyzes the specified elements (such as speed element, pressure element, etc.) in the operation status data and conforms to the fault detection model, the fault phenomenon associated with the fault detection model is taken as the first fault phenomenon of the operation status data.

[0085] In application, through the local fault detection service, the operation status data of the die-casting machine can be monitored in real time, and the first fault phenomenon associated with it can be quickly identified according to the preset fault detection model, improving the timeliness and accuracy of fault detection.

[0086] Step S202, retrieve the first fault model adapted to the first fault phenomenon from the local knowledge base, where the first fault model is used to store at least one fault cause that triggers the first fault phenomenon and the inspection operations associated with each fault cause.

[0087] In application, the fault model can exist in the form of a knowledge model. The control device retrieves from the local knowledge base the first fault model adapted to the first fault phenomenon with the first fault phenomenon as the index. The first fault model includes at least one fault cause that triggers the first fault phenomenon and the inspection operations required to repair each fault cause.

[0088] In application, retrieving the first fault model that matches the first fault phenomenon from the local knowledge base, which contains the possible fault causes that trigger the first fault phenomenon and their corresponding inspection operations, helps to quickly locate the specific cause of the fault.

[0089] Step S203, determine the local detection result based on the first fault phenomenon and the first fault model.

[0090] In application, the control device can directly take the first fault phenomenon and the first fault model as the local detection result. It can also adjust the first fault model (such as deleting the excluded fault causes) and then take the first fault phenomenon and the new first fault model as the local detection result.

[0091] In application, based on the first fault phenomenon and the first fault model, the local detection result can be automatically determined, providing a clear fault handling guide for the operator, simplifying the fault handling process, and improving the fault efficiency. Through the information provided by the local fault detection and the fault model, the operator can quickly take the correct inspection operations, reduce the fault troubleshooting time, thereby improving the maintenance efficiency and reducing the downtime.

[0092] In this embodiment, through real-time monitoring, rapid fault location, and guiding fault handling, the maintenance efficiency and production efficiency of the die-casting machine are effectively improved, the maintenance cost is reduced, and the continuity and stability of production are ensured.

[0093] In one embodiment, the local fault detection service includes multiple diagnostic units, and each diagnostic unit includes at least one feature recognition point, such as Figure 5 As shown, the process of implementing step S102 by combining multiple diagnostic units includes the following steps S301 to S304:

[0094] Step S301, based on each diagnostic unit, perform parallel diagnostic processing on the operation status data respectively to obtain the specified feature recognition points matching the operation status data.

[0095] In application, the control device performs inference analysis on the operation status data through each diagnostic unit of the local detection service, and generates the operation status data and the feature recognition points included in each targeted diagnostic unit. The feature recognition point refers to the value of the specified element in the operation status data or the change of the specified element, which is different from the reference information corresponding to the normal operation status data, and is also an important indicator for confirming faults.

[0096] That is to say, the diagnostic unit calculates the feature recognition point based on the operation status data. When the feature recognition point conforms to a certain fault model, it is confirmed that the fault has occurred, and the cause of the fault and the inspection measures in the provided fault model are retrieved.

[0097] Exemplarily, as Figure 6 shown, there are multiple pieces of operation status data. For the operation status data numbered 28033, there are obvious abnormalities in slow speed, fast speed, fast start point, pressure build-up time, and filling stroke in the operation status data. The feature recognition point - the fast speed value reaches 8.09 m / s, far exceeding the normal value of 5.20 m / s. As Figure 7 shown, the normal injection curve numbered 28029 Figure 7 in (a) and the abnormal curve numbered 28033 Figure 7 in (b) are compared. a1 and b1 are the position curves of the position element, a2 and b2 are the pressure curves of the pressure element, and a3 and b3 are the speed curves of the speed element. The control device runs the die-casting machine fault detection inference mechanism, referring to Figure 7In (b) of the figure, the process of inferring and analyzing the operating state data is as follows: 1) There are steps in the b1-hammer head position curve, and the hammer head may be stuck; 2) There is a jitter phenomenon in the speed curve of the b3-slow speed stage, which is also caused by the hammer head jamming. Due to the closed-loop control of the injection speed, the fluctuation situation is amplified; 3) When the hammer head position is stuck in the middle, due to the reduction of the injection speed, the closed-loop control will automatically increase the opening of the outlet servo valve, resulting in the continuous discharge of hydraulic oil in the outlet oil cylinder, and the outlet pressure will continue to decrease; 4) When the outlet pressure continues to decrease, the inlet pressure will gradually act entirely on the hammer jamming part; 5) The hammer jamming point continuously holds back the inlet pressure, and when it loosens, the inlet pressure is fully released; 6) At this time, there is no pressure buffer at the outlet, resulting in the speed directly reaching 8.09 m / s. The corresponding fault identification points are: 1) When the hammer head stops, the control voltage of the outlet servo valve is closed-loop adjusted from 0.74 V to 1.65 V; 2) When the hammer head stops, the outlet pressure drops from 181 bar to 6 bar; 3) The inlet pressure remains at about 151 bar before and after the stop position; 4) The start time of the position stop is 3330 ms, and the recovery time of the movement is 3764 ms, lasting about 434 ms.

[0098] Based on the above analysis process, the characteristic identification points that can be inferred to cause the fault phenomenon - hammer jamming are as follows: 1) Product quality characteristics, 2) Injection speed characteristics, 3) Injection resistance characteristics, etc. In addition, combined with the preset knowledge of the die-casting machine mechanical design theory, the following characteristic identification points can also be added: 4) Hammer head temperature characteristics, 6) Hammer head lubrication characteristics, 7) Hammer head mismatch characteristics, etc.

[0099] Correspondingly, as Figure 8 shown is the model structure of the fault model corresponding to the fault phenomenon - hammer jamming. Based on this fault model structure, the fault causes related to the fault phenomenon - hammer jamming can be determined, at least one inspection operation can be provided for each fault cause, and corresponding prompts can also be displayed on the human-machine interaction interface. For the fault cause 1) Abnormal cooperation between the hammer head and the charging barrel, the required inspection operation 1) Observe whether there is aluminum skin near the feeding part. For the fault cause 2) Abnormal hammer head lubrication, the required inspection operation 2) Check the remaining amount of lubricating oil and the sensor. For the fault cause 3) Abnormal hammer head cooling, the required detection operation 3) Check the hammer head temperature and the sensor, and at the same time, corresponding inspection operations are provided for each fault cause.

[0100] Step S302, based on each of the specified characteristic identification points, match with the fault models in the local knowledge base to obtain the specified fault models that the operating state data conforms to.

[0101] In the application, based on multiple characteristic identification points extracted from the operating state data, the target fault model can be determined from the preset fault models.

[0102] Continuing with the previous example, assume that multiple feature recognition points extracted from the operating state data match the feature recognition points of the fault model corresponding to "Fault Phenomenon - Hammer Jamming" (speed < 0.05 m / s and inlet pressure > 120 bar and outlet pressure < 10 bar and hammer head position < (ending position of material feeding - 50) mm). Then, the fault model corresponding to "Fault Phenomenon - Hammer Jamming" is taken as the target fault model.

[0103] Step 303: Determine the fault phenomenon of the specified fault model as the first fault phenomenon associated with the operating state data.

[0104] In an application, the fault recognition points of the operating state data can match multiple target fault models, and each target fault model corresponds to a fault phenomenon. The control device takes the fault phenomenon associated with each target fault model as the first fault phenomenon.

[0105] Step S304: Determine the local detection result based on the first fault phenomenon and the first fault model.

[0106] In this embodiment, through reasoning and analysis of the operating state data, the fault recognition points can be effectively determined, thereby more accurately locating the position or source of potential faults. According to the determined fault recognition points, the most relevant one is selected from the preset fault models as the target fault model, so that fault detection can be more targeted, improving the detection efficiency and accuracy. By determining the fault phenomenon associated with the target fault model as the first fault phenomenon, the fault type associated with the current operating state data can be quickly identified, thus accelerating the fault handling process. This embodiment effectively improves the accuracy and efficiency of fault detection, helps reduce downtime and maintenance costs, and at the same time enhances the continuity and stability of production.

[0107] In one embodiment, the multiple diagnostic units include: a numerical control diagnostic unit, a mechanical diagnostic unit, a hydraulic diagnostic unit, and an electrical diagnostic unit; wherein, the numerical control diagnostic unit is used to detect the power components and numerical control components of the equipment; the mechanical diagnostic unit is used to check mechanical parts and actions; the hydraulic diagnostic unit is used to detect hydraulic parts and actions; the electrical diagnostic unit is used to detect electrical parts and control systems.

[0108] In an application, a numerical control diagnosis unit is used to establish a connection between the equipment power components and the numerical control components of a die-casting machine through a network to read data in real time, such as a servo pump station group, a servo motor, etc. The characteristics monitored by the numerical control diagnosis unit include system current, system pressure, rotational speed, load, temperature, magnetic declination, etc. A mechanical diagnosis unit is used to inspect mechanical components and movements, such as installing vibration, strain, temperature sensors, etc. at positions such as the die-casting machine frame, platen, and tie bar gate; the characteristics monitored by the mechanical diagnosis unit at least include parameters such as vibration, strain, and temperature. A hydraulic diagnosis unit detects hydraulic components and movements, including installing sensors such as pressure, flow rate, and temperature in cylinders and oil circuits such as mold locking and opening, injection, etc., and establishing communication connections with hydraulic control servo valves, proportional valves, etc.; the characteristics monitored by the hydraulic diagnosis unit include data such as the system pressure, system flow rate, pressure, flow rate, temperature, control voltage, feedback voltage, etc. of the hydraulic oil circuit. An electrical diagnosis unit is used to detect electrical components and control systems (such as input / output modules, action responses, interference, etc.), including establishing communication connections with one or more PLC controllers, intelligent meters, etc. to read system status data; the characteristics monitored by the electrical diagnosis unit at least include system interference, response efficiency, production cycle time, energy consumption, voltage, current, etc.

[0109] In an application, based on the fact that the state data sources of the above-mentioned diagnosis units are not completely the same, the diagnoses of the respective diagnosis units have different models and algorithms.

[0110] In this embodiment, by refining feature recognition points through the diagnosis unit, it is possible to more accurately focus on the key parameters that may cause faults and improve the pertinence of fault detection.

[0111] In one embodiment, the control device can also display the value changes of each feature recognition point in a preset style (such as a pie chart, a line chart, etc.) through a human-machine interface. At the same time, after determining the target fault model, it can also prompt the required inspection operations through the human-machine interface.

[0112] Exemplarily, as Figure 7 shown in the visualization result, the value changes of the speed feature, pressure feature, and position feature in the operating state data can be displayed in the form of a line chart.

[0113] In this embodiment, the information of the specified elements is displayed graphically through the human-machine interface, enabling maintenance personnel to intuitively understand the state change trend of the equipment and facilitating the discovery of abnormal patterns or trends. Based on the visualization result, maintenance personnel or the system can more quickly identify the fault points, reduce the time for fault diagnosis, and improve the maintenance efficiency.

[0114] In one embodiment, as Figure 9 shown, the implementation process of step S103 includes the following steps S401 to step S403:

[0115] Step S401: Through the remote fault detection service, in combination with the cloud inference engine and the remote knowledge base, perform real-time inference and analysis on the operation status data to determine the second fault phenomenon that the operation status data conforms to.

[0116] In an application, the control device performs real-time inference and analysis on the operation status data through the remote fault detection service, using the knowledge base in die-casting machine fault diagnosis, to obtain the second fault phenomenon that the operation status data conforms to. In this way, by combining the knowledge base, the operation status data can be evaluated from multiple perspectives, which helps to comprehensively judge the cause of the fault, avoid limitations under a single perspective, can provide a higher level of fault diagnosis ability, and improve the accuracy and depth of fault identification.

[0117] Step S402: Retrieve from the remote knowledge base a second fault model adapted to the second fault phenomenon, where the remote knowledge base is used to store fault phenomena associated with various different types of die-casting machines and the fault models of the fault phenomena.

[0118] In an application, the remote knowledge base contains fault phenomena and fault models associated with various different types of die-casting machines, which can provide rich reference cases and solutions for fault detection, and helps to improve the comprehensiveness and accuracy of fault diagnosis. By retrieving from the remote knowledge base a second fault model adapted to the second fault phenomenon, the specific cause of the fault and its possible solutions can be located, reducing the fault troubleshooting time. Retrieving from the remote knowledge base can obtain more comprehensive hidden fault phenomena corresponding to the operation status data, and obtain the target fault model determined based on multi-source information (operation status data of various different types of die-casting machines).

[0119] Step S403: Based on the second fault phenomenon and the second fault model, determine the remote detection result.

[0120] In an application, the control device can directly use the second fault phenomenon and the second fault model as the remote detection result. It can also adjust the second fault model (such as deleting the excluded cause of the fault) and then use the second fault phenomenon and the new second fault model as the remote detection result.

[0121] In this embodiment, through the remote fault detection service combined with the knowledge base for fault diagnosis, and using the remote knowledge base for retrieval and analysis of fault phenomena, the accuracy and efficiency of fault diagnosis can be improved, which helps to reduce the downtime and enhance the maintenance efficiency and production efficiency.

[0122] In one embodiment, as Figure 10 shown, the implementation process of step S104 includes the following steps S501 to S503:

[0123] Step S501: Perform a difference analysis on the first fault model of the first fault phenomenon in the local detection result and the second fault model of the second fault phenomenon in the remote detection result.

[0124] Step S502: Based on the analysis result, determine the potential fault model, and determine the potential diagnostic unit and potential feature identification points corresponding to the potential fault model.

[0125] In application, the control device decouples the association between the fault phenomenon and the operation state data on the cloud platform through the remote fault detection service, establishes a potential fault model representing the association between the fault phenomenon and multi-source information, derives the potential diagnostic unit and potential feature identification points of the potential fault model. The potential diagnostic unit is actually the identification and judgment logic that can detect potential fault phenomena not detected by the local fault detection service. And download the associated fault model to the local and update the local fault detection service.

[0126] Step S503: Update the local fault detection service based on the potential fault model, the potential diagnostic unit, and the potential feature identification points.

[0127] In application, based on the potential fault model, the potential diagnostic unit, and the potential feature identification points, send the remote diagnosis result to the local device to update the local fault detection service.

[0128] In this embodiment, combined with the high computing power and strong algorithm of the remote fault detection service, the fault diagnosis result is further verified and refined to improve the accuracy. Finally, the local detection result is supplemented and corrected by the remote detection result to ensure that the fault detection result is more comprehensive and reliable. In this way, the fault detection accuracy of the die-casting machine is improved through the dual fault detection mechanism.

[0129] In one embodiment, the control device realizes the sorting of fault causes as follows: Based on the updated local fault detection service, determine the target fault phenomenon of the operation state data; determine the fault weight of each fault cause in the target fault model corresponding to the target fault phenomenon for the target fault phenomenon; according to each of the fault weights, sort the fault causes in the target fault model to obtain the fault detection result of the operation state data.

[0130] In an application, a control device reads the fault weights set for each fault cause in a target fault model. Among them, the fault weights can be set based on the repair rate of the inspection operation for the fault cause with respect to the fault phenomenon. The fault weights can be used to characterize the importance of different fault causes. Sort the priorities of each fault cause according to the fault weights. The priority of the inspection operation corresponding to the fault cause with a high fault weight is higher than that of the inspection operation corresponding to the fault cause with a low fault weight. Finally, use the target fault phenomenon and the sorted target fault model as the fault detection result of the operating state data. The sorted fault detection result helps to reduce the possibility of ignoring important faults due to dealing with low-priority faults, thereby reducing the occurrence of misjudgment and missed judgment, and can provide a clear processing order for maintenance personnel, which helps to make more reasonable maintenance decisions.

[0131] In this embodiment, by calculating the fault weights and sorting the fault causes, it helps to improve the efficiency and accuracy of fault diagnosis, optimize resource allocation, improve the quality of maintenance decisions, and enhance the executability of maintenance plans.

[0132] The embodiment of the present application also provides a fault detection device for a die-casting machine, which is used to execute the steps in the embodiment of the fault detection method for the die-casting machine described above. As Figure 11 shown, the fault detection device 800 for the die-casting machine provided by the embodiment of the present application includes:

[0133] An acquisition module 810, configured to acquire real-time operating state data of the die-casting machine during the production process.

[0134] A local detection module 820, configured to perform real-time detection on the operating state data through a local fault detection service to obtain a local detection result.

[0135] A remote detection module 830, configured to perform fault detection on the operating state data through a remote fault detection service to obtain a remote detection result.

[0136] An update module 840, configured to update the local fault detection service based on the difference between the local detection result and the remote detection result.

[0137] A target detection module 850, configured to perform detection on the operating state data based on the updated local fault detection service to obtain the target detection result of the operating state data.

[0138] In one embodiment, the local detection module is further configured to perform fault identification on the operation status data based on preset feature identification points of the local fault detection service to obtain a first fault phenomenon; retrieve a first fault model adapted to the first fault phenomenon from the local knowledge base, where the first fault model is used to store at least one fault cause that triggers the first fault phenomenon and inspection operations associated with each fault cause; and determine a local detection result based on the first fault phenomenon and the first fault model.

[0139] In one embodiment, the local fault detection service includes multiple diagnostic units, and each diagnostic unit includes at least one feature identification point. The local detection module is further configured to perform parallel diagnostic processing on the operation status data based on each diagnostic unit respectively to obtain designated feature identification points matched by the operation status data; match the designated feature identification points with the fault models in the local knowledge base to obtain a designated fault model that the operation status data conforms to; determine the fault phenomenon of the designated fault model as the first fault phenomenon associated with the operation status data; and determine a local detection result based on the first fault phenomenon and the first fault model.

[0140] In one embodiment, the multiple diagnostic units include: a numerical control diagnostic unit, a mechanical diagnostic unit, a hydraulic diagnostic unit, and an electrical diagnostic unit; wherein, the numerical control diagnostic unit is used to detect the equipment power components and numerical control components; the mechanical diagnostic unit is used to inspect mechanical parts and actions; the hydraulic diagnostic unit is used to detect hydraulic parts and actions; and the electrical diagnostic unit is used to detect electrical parts and control systems.

[0141] In one embodiment, the remote detection module is further configured to perform real-time inference analysis on the operation status data through the remote fault detection service in combination with the cloud inference engine and the remote knowledge base to determine a second fault phenomenon that the operation status data conforms to; retrieve a second fault model adapted to the second fault phenomenon from the remote knowledge base, where the remote knowledge base is used to store fault phenomena associated with various different types of die-casting machines and fault models of the fault phenomena; and determine a remote detection result based on the second fault phenomenon and the second fault model.

[0142] In one embodiment, the update module is further configured to perform a difference analysis on the first fault model of the first fault phenomenon in the local detection result and the second fault model of the second fault phenomenon in the remote detection result; determine a potential fault model based on the analysis result, and determine the potential diagnostic unit and potential feature identification point corresponding to the potential fault model; and update the local fault detection service based on the potential fault model, potential diagnostic unit, and potential feature identification point.

[0143] In one embodiment, the update module is further configured to determine a target fault phenomenon of the operation status data based on the updated local fault detection service; determine a fault weight of each fault cause in the target fault model corresponding to the target fault phenomenon for the target fault phenomenon; and sort the fault causes in the target fault model according to the respective fault weights to obtain a fault detection result of the operation status data.

[0144] In applications, each module in the fault detection device of the die-casting machine can be a software program module, can also be implemented by different logic circuits integrated in the processor, or can also be implemented by multiple distributed processors.

[0145] Figure 12 FIG. is a schematic structural diagram of a control device for implementing the fault detection method of the die-casting machine of the present application provided by an embodiment of the present application. As Figure 12 shown, the control device 900 of this embodiment includes: at least one processor 910 ( Figure 12 only one is shown in the figure), a processor, a memory 920, and a computer program 930 stored in the memory 920 and executable on the at least one processor 910. When the processor 910 executes the computer program 930, the steps in any of the above-mentioned embodiments of the fault detection method of the die-casting machine are implemented.

[0146] The control device 900 may include, but is not limited to, a processor 910 and a memory 920. Those skilled in the art can understand that Figure 12 merely an example of the control device 900, which does not constitute a limitation on the control device 900, and may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0147] The processor 910 may be a central processing unit (CPU), and the processor 910 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0148] In some embodiments, the memory 920 may be an internal storage unit of the control device 900, such as the hard disk or memory of the control device 900. In other embodiments, the memory 920 may also be an external storage device of the control device 900, such as a plug-in hard disk equipped on the control device 900, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 920 may also include both the internal storage unit and the external storage device of the control device 900. The memory 920 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 920 may also be used to temporarily store data that has been output or will be output.

[0149] It should be noted that for the content such as information interaction and execution process between the above-mentioned device / units, since it is based on the same concept as the method embodiment of the present application, for its specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0150] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

[0151] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0152] The embodiment of the present application provides a computer program product. When the computer program product runs on a control device, the control device is caused to execute the steps in the above-mentioned method embodiments.

[0153] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the control device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunications signal.

[0154] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0156] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical, mechanical, or other form.

[0157] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting a fault of a die casting machine, characterized in that: include: Obtain real-time operating status data of the die-casting machine during the production process; By using a local fault detection service, the operating status data is detected in real time to obtain a local detection result; Performing fault detection on the operating status data through a remote fault detection service to obtain a remote detection result; Based on the difference between the local detection result and the remote detection result, updating the local fault detection service; Based on the updated local fault detection service, the running status data is detected to obtain a target detection result of the running status data.

2. The fault detection method for a die casting machine according to claim 1, characterized in that: The real-time detection of the operating status data by the local fault detection service to obtain a local detection result includes: Based on the preset feature identification points of the local fault detection service, fault identification is performed on the operating status data to obtain a first fault phenomenon; Retrieving a first fault model adapted to the first fault phenomenon from a local knowledge base, wherein the first fault model is used to store at least one fault cause causing the first fault phenomenon and an inspection operation associated with each of the fault causes; Based on the first fault phenomenon and the first fault model, a local detection result is determined.

3. The fault detection method for a die casting machine according to claim 1, characterized in that: The local fault detection service comprises a plurality of diagnostic units, each of which comprises at least one characteristic identification point. The real-time detection of the operating status data by the local fault detection service to obtain a local detection result includes: Based on each diagnosis unit, the operation status data is respectively diagnosed and processed in parallel to obtain a designated feature identification point matched by the operation status data; Based on each of the designated feature identification points, matching is performed with the fault model in the local knowledge base to obtain the designated fault model that the operating status data conforms to; Determining the fault phenomenon of the specified fault model as the first fault phenomenon associated with the operating status data; Based on the first fault phenomenon and the first fault model, a local detection result is determined.

4. The fault detection method for a die casting machine according to claim 3, characterized in that: The plurality of diagnostic units include: a numerical control diagnostic unit, a mechanical diagnostic unit, a hydraulic diagnostic unit, and an electrical diagnostic unit; Wherein, the CNC diagnostic unit is used to detect the power components and CNC components of the equipment; The mechanical diagnostic unit is used to check mechanical parts and movements; The hydraulic diagnostic unit is used to detect hydraulic components and actions; The electrical diagnostic unit is used to detect electrical components and control systems.

5. The fault detection method for a die casting machine according to claim 1, characterized in that: The remote fault detection service is used to perform fault detection on the operation status data to obtain a remote detection result, including: Through the remote fault detection service, the cloud inference engine and the remote knowledge base are combined to perform real-time reasoning and analysis on the operating status data to determine the second fault phenomenon that the operating status data corresponds to; Retrieving a second fault model adapted to the second fault phenomenon from a remote knowledge base, wherein the remote knowledge base is used to store fault phenomena associated with various types of die-casting machines and fault models of the fault phenomena; Based on the second fault phenomenon and the second fault model, a remote detection result is determined.

6. The fault detection method for a die casting machine according to claim 1, characterized in that: The updating of the local fault detection service based on the difference between the local detection result and the remote detection result includes: Performing difference analysis on a first fault model of a first fault phenomenon of the local detection result and a second fault model of a second fault phenomenon of the remote detection result; Based on the analysis results, determine a potential fault model, and determine a potential diagnosis unit and a potential feature identification point corresponding to the potential fault model; The local fault detection service is updated based on the potential fault model, the potential diagnostic unit and the potential feature identification point.

7. The fault detection method for a die casting machine according to claim 1, characterized in that: The updated local fault detection service detects the running status data to obtain a target detection result of the running status data, including: Determining a target fault phenomenon of the operating status data based on the updated local fault detection service; Determine a fault weight of each fault cause in a target fault model corresponding to the target fault phenomenon for the target fault phenomenon; According to each of the fault weights, each fault cause in the target fault model is sorted to obtain a target detection result of the operating status data.

8. A fault detection device for a die casting machine, characterized in that: include: An acquisition module is used to acquire real-time operating status data of the die-casting machine during the production process; A local detection module, used to perform real-time detection on the operating status data through a local fault detection service to obtain a local detection result; A remote detection module, used to perform fault detection on the operating status data through a remote fault detection service to obtain a remote detection result; An updating module, configured to update the local fault detection service based on a difference between the local detection result and the remote detection result; The target detection module is used to detect the running status data based on the updated local fault detection service to obtain the target detection result of the running status data.

9. A control device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the fault detection method for the die casting machine according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fault detection method for a die casting machine according to any one of claims 1 to 7 is implemented.

Images