Intelligent early warning method, device, equipment and storage medium for ring rolling mill tooling failure

Abstract

The present disclosure provides an intelligent early warning method, device, equipment and storage medium for ring rolling machine tooling failure, which relates to the technical field of industrial production, specifically to the technical fields of deep learning, data transmission, etc., and can be applied to the scenario of manufacturing aviation ring forgings. The specific implementation scheme includes: obtaining the target type of aviation ring forgings to be ring-rolled by the ring rolling equipment; inputting the target type into the mandrel prediction model, and outputting the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model; determining the remaining working time of the mandrel based on the predicted working time and the working time of the mandrel; determining the predicted fracture time of the mandrel based on the remaining working time; and sending fault early warning information for the mandrel based on the predicted fracture time, and the fault early warning information is used to prompt the user to replace the mandrel. The present disclosure can reduce the impact of replacing the mandrel on the ring rolling efficiency and improve the ring rolling efficiency.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial production technology, specifically to technical fields such as deep learning and data transmission, and can be applied in the scenario of manufacturing aviation ring forgings, and in particular to an intelligent early warning method, device, equipment and storage medium for ring rolling machine tooling failure. Background Art

[0002] Aviation ring forgings are one of the important parts in aviation engines. Their structure and mechanical properties play a vital role in the performance, reliability and safety of the engine. Ring rolling is an important step in the manufacturing process of aviation ring forgings. Ring rolling refers to a plastic processing process that uses ring rolling equipment to reduce the wall thickness, expand the diameter, and form the cross-sectional profile of the ring. Ring rolling equipment can include a ring rolling machine, also known as a rolling machine or a hole expander. The ring rolling equipment usually consists of the following parts: a rolling mill, a heating system, an axial thrust device, and a mandrel. Among them, the mandrel, as an important component of the ring rolling equipment, plays a key role in forced deformation, thermal control, and support positioning during the ring rolling process. The design and processing quality of the mandrel are of great significance to ensuring the quality and precision of the finished ring rolled product.

[0003] Currently, in the manufacturing process of aviation ring forgings, when the mandrel of the ring rolling equipment breaks or has quality problems, the mandrel will be replaced.

[0004] However, the current method of replacing the mandrel after it breaks or has quality problems will affect the ring rolling efficiency. Summary of the invention

[0005] The present invention provides an intelligent early warning method, device, equipment and storage medium for ring rolling machine tooling failure, which can reduce the impact of replacing the mandrel on the ring rolling efficiency and improve the ring rolling efficiency.

[0006] According to a first aspect of the present disclosure, there is provided an intelligent early warning method for ring rolling mill tooling failure, the method comprising:

[0007] Obtain the target type of aviation ring forgings ring-rolled by the ring rolling equipment; input the target type into the mandrel prediction model, and output the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model; determine the remaining working time of the mandrel based on the predicted working time and the working time of the mandrel; determine the predicted fracture time of the mandrel based on the remaining working time; send fault warning information to the mandrel based on the predicted fracture time, and the fault warning information is used to prompt the user to replace the mandrel.

[0008] According to a second aspect of the present disclosure, an intelligent early warning device for ring rolling mill tooling failure is provided, the device comprising: an acquisition unit, an output unit, a determination unit, and a sending unit.

[0009] An acquisition unit is used to acquire a target type of aviation ring forgings ring-rolled by a ring rolling device; an output unit is used to input the target type into a mandrel prediction model, and output the predicted working time of the mandrel of the ring rolling device through the mandrel prediction model; a determination unit is used to determine the remaining working time of the mandrel based on the predicted working time and the working time of the mandrel; the determination unit is also used to determine the predicted fracture time of the mandrel based on the remaining working time; a sending unit is used to send fault warning information for the mandrel based on the predicted fracture time, and the fault warning information is used to prompt the user to replace the mandrel.

[0010] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the first aspect.

[0011] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method according to the first aspect.

[0012] According to a fifth aspect of the present disclosure, there is provided a computer program product, comprising a computer program, which implements the method according to the first aspect when executed by a processor.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0015] Figure 1 A schematic flow chart of an intelligent early warning method for ring rolling mill tooling failure provided by an embodiment of the present disclosure;

[0016] Figure 2 Another schematic diagram of the process of the intelligent early warning method for ring rolling mill tooling failure provided by the embodiment of the present disclosure;

[0017] Figure 3 The embodiments of the present disclosure provide Figure 1 A schematic diagram of an implementation process of S105;

[0018] Figure 4 The embodiments of the present disclosure provide Figure 1 A schematic diagram of an implementation process of S104;

[0019] Figure 5A schematic diagram of the composition of an intelligent early warning device for ring rolling mill tooling failure provided by an embodiment of the present disclosure;

[0020] Figure 6 Another schematic diagram of the components of the intelligent early warning device for ring rolling mill tooling failure provided by the embodiment of the present disclosure;

[0021] Figure 7 The present disclosure is provided as a schematic block diagram of an example electronic device 700 that can be used to implement the present disclosure. DETAILED DESCRIPTION

[0022] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] It should be understood that in the embodiments of the present disclosure, the character " / " generally indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", etc. are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0024] Aviation ring forgings are one of the important parts in aviation engines. Their structure and mechanical properties play a vital role in the performance, reliability and safety of the engine. Ring rolling is an important step in the manufacturing process of aviation ring forgings. Ring rolling refers to a plastic processing process that uses ring rolling equipment to reduce the wall thickness, expand the diameter, and form the cross-sectional profile of the ring. Ring rolling equipment can include a ring rolling machine, also known as a rolling machine or a hole expander. The ring rolling equipment usually consists of the following parts: a rolling mill, a heating system, an axial thrust device, and a mandrel. Among them, the mandrel, as an important component of the ring rolling equipment, plays a key role in forced deformation, thermal control, and support positioning during the ring rolling process. The design and processing quality of the mandrel are of great significance to ensuring the quality and precision of the finished ring rolled product.

[0025] Currently, in the manufacturing process of aviation ring forgings, when the mandrel of the ring rolling equipment breaks or has quality problems, the mandrel will be replaced.

[0026] However, the current method of replacing the mandrel after it breaks or has quality problems will affect the ring rolling efficiency.

[0027] For example, aviation ring forgings are a key component widely used in high-strength and high-reliability fields such as aerospace. The manufacturing process of aviation ring forgings generally includes the following steps: material preparation, pre-mold and blank preparation, heating, ring rolling, finishing, heat treatment, inspection, surface treatment, finished product inspection and packaging. Ring rolling is an important step in the manufacturing process of aviation ring forgings. Ring rolling refers to the process of rolling a metal blank into a ring-shaped cross-section through a rolling process. During the ring rolling process, the metal blank is clamped between two rollers, and through the action of rolling, the metal blank gradually deforms into a ring shape. During the ring rolling process, a mandrel is required, usually located in the central hollow inside the metal blank. The function of the mandrel is to ensure that the metal blank produces a ring-shaped cross-section during the ring rolling process and to provide positioning and support.

[0028] At present, in the manufacturing process of aviation ring forgings, when the mandrel of the ring rolling equipment fails, is damaged or has other problems that cannot be repaired, the mandrel needs to be replaced immediately. However, the current method of replacing the mandrel after the mandrel breaks or has quality problems will cause the ring rolling to be suddenly interrupted, thereby affecting the ring rolling efficiency.

[0029] Against this background technology, the present disclosure provides an intelligent early warning method for ring rolling machine tooling failure, which can reduce the impact of replacing the mandrel on the ring rolling efficiency and improve the ring rolling efficiency.

[0030] Exemplarily, the execution subject of the intelligent early warning method for ring rolling mill tooling failure may be a computer or a server, or may be other equipment with data processing capabilities. The execution subject of the method is not limited here.

[0031] In some embodiments, the server may be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster. The present disclosure does not limit the specific implementation of the server.

[0032] Figure 1 The figure is a flow chart of the intelligent early warning method for ring rolling mill tooling failure provided by the embodiment of the present disclosure. Figure 1 As shown, the method may include S101-S105.

[0033] S101, obtaining a target type of aviation ring forgings ring-rolled by a ring rolling equipment.

[0034] S102, inputting the target type into a mandrel prediction model, and outputting the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model.

[0035] Exemplarily, the target type may include one or more. Different target types may be represented by corresponding identifiers. The identifier of the target type of the aviation ring forging may be input into the mandrel prediction model, and the predicted working time of the mandrel of the ring rolling equipment may be output through the mandrel prediction model. The predicted working time of the mandrel indicates the total working time of the mandrel from the beginning of use to the occurrence of a failure (such as a break). The mandrel prediction model is obtained by training with the identifier of the target type of the aviation ring forging as input and the predicted working time of the mandrel as output. The obtained mandrel prediction model can output the predicted working time of the mandrel when the ring rolling equipment performs ring rolling on aviation ring forgings of different target types according to the target types of different aviation ring forgings.

[0036] By way of example, the mandrel prediction model may include an input layer, an embedding layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer. The input layer receives the identifier corresponding to the target type of the aviation ring forging as the input of the mandrel prediction model. The embedding layer converts the input identifier into a vector representation of a fixed size. The embedding layer maps the discrete input identifier into a continuous vector space by learning, thereby extracting the semantic information between the identifiers. The convolution layer then uses a set of learnable convolution kernels to perform a convolution operation on the vector sequence output by the embedding layer to extract local features in the input identifier sequence. The size and number of the convolution kernels can be adjusted according to the specific task. The pooling layer reduces the model parameters and computational complexity by reducing the length of the feature sequence. Common pooling operations include maximum pooling and average pooling. The feature vector output by the pooling layer is then converted into a one-dimensional vector and connected to a fully connected layer. The fully connected layer contains multiple neurons for learning the complex relationship between the input identifier sequence and the predicted working time of the mandrel. The output layer may be one or more neurons according to the specific needs of predicting the working time. For example, a fully connected layer with a single neuron can be used to predict working hours.

[0037] Based on the above embodiment, for example, the target type identification A of the aviation ring forging of type A is input into the mandrel prediction model, and the embedding layer of the mandrel prediction model can convert the input target type identification A into a vector representation of a fixed size, and then the convolution layer uses a set of learnable convolution kernels to perform a convolution operation on the vector of the target type identification A output by the embedding layer to extract the local features in the input target type identification A, and the pooling layer converts the processed target type identification A output by the convolution layer into a one-dimensional vector and connects it to a fully connected layer, and the fully connected layer learns the complex relationship between the input target type identification A and the predicted working time of the mandrel, and finally outputs the predicted working time of the mandrel when the ring rolling equipment performs ring rolling on the aviation ring forging of type A corresponding to the target type identification A through the output layer. Similarly, the target type identification B of the aviation ring forging of type B is input into the mandrel prediction model, and the mandrel prediction model can output the predicted working time of the mandrel when the ring rolling equipment performs ring rolling on the aviation ring forging of type B.

[0038] S103: Determine the remaining working time of the mandrel according to the predicted working time and the working time of the mandrel.

[0039] For example, the remaining working time of the mandrel may be obtained by subtracting the working time of the mandrel from the predicted working time of the mandrel.

[0040] Based on the above embodiment, for example, assuming that the mandrel prediction model outputs a predicted working time of the mandrel of 10 hours, and it is known that the working time of the mandrel is 4 hours, it can be calculated that the remaining working time of the mandrel is 6 hours.

[0041] S104. Determine the predicted fracture time of the mandrel according to the remaining working time.

[0042] For example, after the remaining working time of the mandrel is determined, the predicted breaking time of the mandrel may be calculated according to the current time and the remaining working time of the mandrel.

[0043] Based on the above embodiment, for example, assuming that the remaining working time of the mandrel is 5 hours and the current time is 10 o'clock, it can be calculated that the predicted breakage time of the mandrel is 15 o'clock.

[0044] S105. Send fault warning information to the mandrel according to the predicted fracture time.

[0045] Among them, the fault warning information is used to prompt the user to replace the core shaft.

[0046] For example, after the predicted breakage time of the mandrel is determined, fault warning information of the mandrel may be sent before the predicted breakage time of the mandrel to prompt the user to replace the mandrel before the mandrel breaks.

[0047] Based on the above embodiment, for example, assuming that the predicted fracture time of the mandrel is determined to be 13 o'clock, a fault warning message for the mandrel may be sent at any time before 13 o'clock to prompt the user to replace the mandrel.

[0048] The present invention obtains the target type of aviation ring forgings to be ring-rolled by a ring rolling device, inputs the target type into a mandrel prediction model, outputs the predicted working time of the mandrel of the ring rolling device through the mandrel prediction model, and then determines the remaining working time of the mandrel based on the predicted working time and the working time of the mandrel, and then determines the predicted fracture time of the mandrel based on the remaining working time, and finally sends fault warning information to the mandrel based on the predicted fracture time, thereby sending the fault warning information to the mandrel before the mandrel breaks to prompt the user to replace the mandrel, which can reduce the impact of replacing the mandrel on the ring rolling efficiency and improve the ring rolling efficiency.

[0049] Figure 2 Another flow chart of the intelligent early warning method for ring rolling mill tooling failure provided by the embodiment of the present disclosure. Figure 2 As shown, the method may include S201 - S202 .

[0050] S201. Obtain sample data corresponding to at least two types of aviation ring forgings, respectively. The sample data corresponding to each type of aviation ring forgings includes: the actual working time of each sample mandrel of the ring rolling equipment when the ring rolling equipment performs ring rolling on the aviation ring forgings of that type within a preset historical period.

[0051] For example, the actual working time of each sample mandrel of the ring rolling equipment when the ring rolling equipment performs ring rolling on each type of aviation ring forgings over a period of time in the past can be calculated.

[0052] Based on the above embodiment, for example, in the past period of time, when the ring rolling equipment performed ring rolling on type A aviation ring forgings, the total duration of the mandrel of the ring rolling equipment from the start of ring rolling to fracture was the actual working duration of the sample mandrel corresponding to type A.

[0053] S202. For sample data corresponding to each type of aviation ring forging, the type is used as input and the actual working time of the sample mandrel corresponding to the type is used as output, and a neural network is trained to obtain a mandrel prediction model.

[0054] Among them, the mandrel prediction model is used to output the predicted working time of the mandrel according to the type of input aviation ring forging.

[0055] For example, assuming that in the past period of time, the actual working time of the sample mandrel corresponding to the aviation ring forging of type A is 10 hours, the actual working time of the sample mandrel corresponding to the aviation ring forging of type B is 15 hours, and the actual working time of the sample mandrel corresponding to the aviation ring forging of type C is 20 hours, A can be used as input and 10 hours as output, B as input and 15 hours as output, and C as input and 20 hours as output to train the neural network and obtain the mandrel prediction model. The obtained mandrel prediction model can output the predicted working time of the mandrel according to the type of aviation ring forging input.

[0056] This embodiment obtains sample data corresponding to at least two types of aviation ring forgings, and the sample data corresponding to each type of aviation ring forgings includes: the actual working time of each sample mandrel of the ring rolling equipment when the ring rolling equipment performs ring rolling on the aviation ring forgings of that type within a preset historical period. For the sample data corresponding to each type of aviation ring forgings, the type is used as input and the actual working time of the sample mandrel corresponding to the type is used as output, and a neural network is trained to obtain a mandrel prediction model. The obtained mandrel prediction model can output the predicted working time of the mandrel according to the input type of aviation ring forgings, thereby providing data support for the subsequent sending of fault warning information on the mandrel.

[0057] Figure 3 The embodiments of the present disclosure provide Figure 1 A schematic diagram of an implementation flow of S105 is shown in FIG. Figure 3 As shown, Figure 1 The illustrated S105 may include S301 - S303 .

[0058] S301, determining whether the moment when the ring rolling of the target type of aviation ring forging ends is after the predicted fracture time.

[0059] S302: When the target type of aviation ring forging finishes ring rolling and after the predicted fracture time, a first fault warning message is sent to the mandrel.

[0060] The first fault warning information is used to prompt the user to replace the mandrel within the ring rolling gap before the predicted fracture time.

[0061] Exemplarily, when the ring rolling equipment is ring rolling an aviation ring forging, there is a ring rolling gap between two adjacent aviation ring forgings. The time when the target type of aviation ring forging ends ring rolling can be determined based on the actual processing scenario, and then it can be determined whether the time when the target type of aviation ring forging ends ring rolling is after the predicted fracture time of the mandrel. When the time when the target type of aviation ring forging ends ring rolling is after the predicted fracture time of the mandrel, the first fault warning information of the mandrel is sent to prompt the user to replace the mandrel in the ring rolling gap before the predicted fracture time of the mandrel.

[0062] Based on the above embodiment, for example, when it is determined that the time when the target type of aviation ring forging ends ring rolling is 20:15 and the predicted fracture time of the mandrel is 18:30, it can be judged that the time when the target type of aviation ring forging ends ring rolling is after the predicted fracture time of the mandrel, that is, the mandrel may break during the ring rolling of the target type of aviation ring forging, so it is necessary to send a first fault warning information to the mandrel to prompt the user to replace the mandrel during the ring rolling gap before the predicted fracture time of the mandrel.

[0063] S303: When the target type of aviation ring forging finishes ring rolling and before the predicted fracture time, send a second fault warning message to the mandrel.

[0064] The second fault warning information is used to remind the user of the remaining working time of the spindle.

[0065] For example, when it is determined that the time when the target type of aviation ring forging finishes ring rolling is 20:15 and the predicted fracture time of the mandrel is 21:30, it can be judged that the time when the target type of aviation ring forging finishes ring rolling is before the predicted fracture time of the mandrel, that is, the predicted fracture time of the mandrel is after the time when the target type of aviation ring forging finishes ring rolling, and the mandrel will not break during the ring rolling of the target type of aviation ring forging. At this time, a second fault warning information for the mandrel can be sent to prompt the user of the remaining working time of the mandrel. For example, the second fault warning information for the mandrel is sent at 19:30, prompting the user that the remaining working time of the mandrel is 2 hours.

[0066] This embodiment determines whether the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time. When the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time, the first fault warning information to the core shaft is sent; when the moment when the target type of aviation ring forging finishes ring rolling is before the predicted fracture time, the second fault warning information to the core shaft is sent. This can improve the effectiveness and accuracy of the fault warning information sent and make the fault warning information sent more suitable for actual scenario requirements.

[0067] In some embodiments, the first fault warning information is specifically used to prompt the user to replace the mandrel at the Kth last ring rolling gap before the predicted break time, where K is an integer greater than 1. The smaller the predicted working time of the mandrel, the larger the value of K.

[0068] For example, when the ring rolling equipment is ring rolling an aviation ring forging, there is a ring rolling gap between two adjacent aviation ring forgings. After determining the predicted fracture time of the mandrel, the user can be prompted to replace the mandrel at the Kth ring rolling gap before the predicted fracture time of the mandrel. K is an integer greater than 1, indicating that the user should be prompted to replace the mandrel at least at the second to last ring rolling gap. The smaller the predicted working time of the mandrel, the earlier the first fault warning information should prompt the user to replace the mandrel relative to the predicted fracture time of the mandrel.

[0069] Based on the above embodiment, for example, when the ring rolling equipment is ring rolling 10 aviation ring forgings, there are 9 ring rolling gaps. If the predicted breakage time is during the ring rolling of the 10th aviation ring forging, the first fault warning information can prompt the user to replace the mandrel at the 8th ring rolling gap or any ring rolling gap before the 8th ring rolling gap. The smaller the predicted working time of the mandrel is, the lower the quality of the mandrel is and the easier it is to break. Therefore, the first fault warning information prompts the user to replace the mandrel earlier.

[0070] This embodiment limits the first fault warning information to specifically prompt the user to replace the mandrel at the Kth last ring rolling gap before the predicted fracture time, where K is an integer greater than 1. This ensures that the mandrel is replaced before the mandrel fractures, thereby reducing the impact of the mandrel fracture on the ring rolling.

[0071] Figure 4 The embodiments of the present disclosure provide Figure 1 A schematic diagram of an implementation flow of S104 is shown in FIG. Figure 4 As shown, Figure 1 The illustrated S104 may include S401 - S402 .

[0072] S401, obtaining the duration of the ring rolling gap of a target type of aviation ring forging and the ring rolling duration of each target type of aviation ring forging.

[0073] S402, determining the predicted fracture time of the mandrel according to the current time, the duration of the ring rolling gap, the ring rolling time, and the remaining working time.

[0074] For example, the predicted fracture time of the mandrel can be calculated by T1=T0+(n+1)t1+n×t0. Wherein, T0 represents the current moment, t0 represents the duration of the ring rolling gap, t1 represents the ring rolling duration, T1 represents the predicted fracture time of the mandrel, n represents the number of ring rolling gaps, and n+1 represents the maximum number of aviation ring forgings that can be ring rolled in the remaining working time. The current moment includes the remaining duration of the current ring rolling.

[0075] Based on the above embodiment, for example, assuming that the duration of the ring rolling gap t0 is 0.5 hours, the ring rolling time t1 is 1 hour, the ring rolling equipment is ring rolling an aviation ring forging at 12 o'clock, and the ring rolling equipment will end the current ring rolling of the aviation ring forging at 12:30. Then the current time may be 12:30. When the maximum number of aviation ring forgings that can be ring rolled within the remaining working time is 5, the number of ring rolling gaps is 4. The predicted fracture time of the core shaft can be calculated as 19:30 through T1=T0+(n+1)t1+n×t0.

[0076] This embodiment obtains the duration of the ring rolling gap of the target type of aviation ring forgings and the ring rolling time of each target type of aviation ring forgings, and determines the predicted fracture time of the mandrel according to the current time, the duration of the ring rolling gap, the ring rolling time, and the remaining working time. This can improve the accuracy of the predicted fracture time of the mandrel, thereby reducing the impact of replacing the mandrel on the ring rolling efficiency and improving the ring rolling efficiency.

[0077] In some embodiments, Figure 1 The shown S103 may also include: determining the remaining working time of the spindle according to the predicted working time, the preset coefficient, and the working time of the spindle, where the preset coefficient is greater than 0 and less than 1.

[0078] Among them, the shorter the predicted working time of the spindle is, the smaller the value of the preset coefficient is.

[0079] Exemplarily, a coefficient can be set in advance. When calculating the remaining working time of the mandrel, the predicted working time of the mandrel is first multiplied by the preset coefficient to obtain a first product, and then the working time of the mandrel is subtracted from the first product to obtain the remaining working time of the mandrel.

[0080] Based on the above embodiment, for example, assuming that the predicted working time of the mandrel is 30 hours, the preset coefficient is 0.9, and the working time of the mandrel is 10 hours, it can be calculated that the remaining working time of the mandrel is 17 hours. The smaller the predicted working time of the mandrel is, the lower the quality of the mandrel is and the easier it is to break. Therefore, the smaller the value of the preset coefficient should be, the shorter the remaining working time of the mandrel will be, so that the predicted breaking time of the mandrel will be determined in advance, and the user can be reminded to replace the mandrel before the mandrel breaks.

[0081] This embodiment determines the remaining working time of the mandrel based on the predicted working time, the preset coefficient, and the working time of the mandrel. It can advance the predicted breakage time of the mandrel, and can ensure that the user is reminded to replace the mandrel before the mandrel breaks, thereby reducing the possibility of replacing the mandrel after it breaks and reducing the impact of replacing the mandrel on the ring rolling efficiency.

[0082] In some embodiments, the target type may include at least one of the following: a nickel-based high-temperature alloy type, a titanium alloy type, a steel type, an aluminum alloy type, and a blade alloy type.

[0083] For example, nickel-based high-temperature alloys are one of the most commonly used materials in the aerospace field, with excellent high-temperature resistance, oxidation resistance and creep resistance. Titanium alloys have high strength, low density and good corrosion resistance, and are widely used in the aviation industry to manufacture high-strength lightweight parts, such as engine blades and structural parts. Certain specific aviation ring forgings need to withstand extreme environments under high strength and high temperature, and high-strength steel materials are a suitable choice at this time. Commonly used steels include martensitic stainless steel, martensitic aging steel and low alloy steel. Aluminum alloys have good strength and light weight characteristics and are widely used in aerospace structural parts and casings. Blade alloys are mainly used to manufacture blades for aircraft engines. These alloys must have high strength and corrosion resistance, and have good high-temperature oxidation resistance. Common blade alloys include single crystal high-temperature alloys and polycrystalline high-temperature alloys.

[0084] In this embodiment, the target type can include at least one of the following by limiting the target type: nickel-based high-temperature alloy type, titanium alloy type, steel type, aluminum alloy type, blade alloy type, so as to improve the richness of the target type and thus improve the accuracy of the prediction of the mandrel prediction model.

[0085] In an exemplary embodiment, the embodiment of the present disclosure further provides an intelligent early warning device for tooling failure of a ring rolling mill, which can be used to implement the intelligent early warning method for tooling failure of a ring rolling mill as described in the aforementioned embodiment. Figure 5 The figure is a schematic diagram of the composition of the intelligent early warning device for ring rolling mill tooling failure provided by the embodiment of the present disclosure. Figure 5 As shown, the device may include: an acquisition unit 501, an output unit 502, a determination unit 503, and a sending unit 504.

[0086] The acquisition unit 501 is used to acquire the target type of the aviation ring forgings ring-rolled by the ring rolling equipment.

[0087] The output unit 502 is used to input the target type into the mandrel prediction model, and output the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model.

[0088] The determination unit 503 is used to determine the remaining working time of the spindle according to the predicted working time and the working time of the spindle.

[0089] The determination unit 503 is further configured to determine a predicted fracture time of the mandrel according to the remaining working time.

[0090] The sending unit 504 is used to send fault warning information for the mandrel according to the predicted fracture time, and the fault warning information is used to prompt the user to replace the mandrel.

[0091] Figure 6 Another schematic diagram of the intelligent early warning device for ring rolling mill tooling failure provided by the embodiment of the present disclosure. Figure 6 As shown, the device may further include: an acquisition unit 601 and a training unit 602.

[0092] The acquisition unit 601 is used to obtain sample data corresponding to at least two types of aviation ring forgings, and the sample data corresponding to each type of aviation ring forgings includes: when the ring rolling equipment performs ring rolling on the aviation ring forgings of the type within a preset historical period, the actual working time of each sample core shaft of the ring rolling equipment.

[0093] The training unit 602 is used to train the neural network for the sample data corresponding to each type of aviation ring forging, taking the type as input and the actual working time of the sample mandrel corresponding to the type as output, to obtain a mandrel prediction model. The mandrel prediction model is used to output the predicted working time of the mandrel according to the input type of aviation ring forging.

[0094] Optionally, the sending unit 504 is specifically used to determine whether the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time; when the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time, a first fault warning information for the mandrel is sent, and the first fault warning information is used to prompt the user to replace the mandrel in the ring rolling gap before the predicted fracture time; when the moment when the target type of aviation ring forging finishes ring rolling is before the predicted fracture time, a second fault warning information for the mandrel is sent, and the second fault warning information is used to prompt the user of the remaining working time of the mandrel.

[0095] Optionally, the first fault warning information is specifically used to prompt the user to replace the mandrel at the Kth last ring rolling gap before the predicted fracture time, where K is an integer greater than 1; wherein, the shorter the predicted working time of the mandrel, the larger the value of K.

[0096] Optionally, the determination unit 503 is specifically used to obtain the duration of the ring rolling gap of the target type of aviation ring forgings and the ring rolling time of each target type of aviation ring forgings; and determine the predicted fracture time of the core shaft based on the current time, the duration of the ring rolling gap, the ring rolling time, and the remaining working time.

[0097] Optionally, the determination unit 503 is specifically configured to determine the remaining working time of the spindle according to the predicted working time, the preset coefficient, and the working time of the spindle, wherein the preset coefficient is greater than 0 and less than 1. The smaller the predicted working time of the spindle, the smaller the value of the preset coefficient.

[0098] Optionally, the target type includes at least one of the following: a nickel-based high-temperature alloy type, a titanium alloy type, a steel type, an aluminum alloy type, and a blade alloy type.

[0099] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0100] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0101] In an exemplary embodiment, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable 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 execute the method described in the above embodiments.

[0102] In an exemplary embodiment, the readable storage medium may be a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to the above embodiments.

[0103] In an exemplary embodiment, a computer program product includes a computer program, and when the computer program is executed by a processor, the method according to the above embodiments is implemented.

[0104] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0105] like Figure 7As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0106] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0107] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the intelligent early warning method for the fault of the ring rolling mill tooling. For example, in some embodiments, the intelligent early warning method for the fault of the ring rolling mill tooling may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the intelligent early warning method for the fault of the ring rolling mill tooling described above may be executed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the intelligent early warning method for ring rolling mill tooling failure in any other appropriate manner (eg, by means of firmware).

[0108] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0110] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0113] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An intelligent early warning method for ring rolling mill tooling failure, the method comprising: Obtain the target type of aviation ring forgings rolled by the ring rolling equipment; Inputting the target type into a mandrel prediction model, and outputting the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model, wherein the mandrel prediction model includes an input layer, an embedding layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer; Determining the remaining working time of the mandrel according to the predicted working time and the working time of the mandrel; Determining a predicted breaking time of the mandrel according to the remaining working time; Sending fault warning information of the mandrel according to the predicted fracture time, wherein the fault warning information is used to prompt a user to replace the mandrel; The step of inputting the target type into a mandrel prediction model and outputting a predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model comprises: Determine a target type identifier corresponding to the target type; Input the target type identifier into the mandrel prediction model, convert the target type identifier into a vector through the embedding layer of the mandrel prediction model and output it; Using a convolution kernel through the convolution layer of the mandrel prediction model, convolve the vector of the target type identifier output by the embedding layer to obtain and output local features in the target type identifier; The local features in the target type identification output by the convolution layer are converted into a one-dimensional vector through the pooling layer of the mandrel prediction model, and connected to the fully connected layer; Learning the relationship between the target type identifier and the predicted working time of the mandrel through the fully connected layer of the mandrel prediction model; The output layer of the mandrel prediction model outputs the predicted working time of the mandrel when the ring rolling equipment performs ring rolling on the aviation ring forging of the target type corresponding to the target type identifier based on the relationship between the target type identifier and the predicted working time of the mandrel.

2. The method according to claim 1, further comprising: Obtain sample data corresponding to at least two types of aviation ring forgings, respectively, wherein the sample data corresponding to each type of aviation ring forgings includes: the actual working time of each sample mandrel of the ring rolling equipment when the ring rolling equipment performs ring rolling on the aviation ring forging of the type within a preset historical period; For the sample data corresponding to each type of aviation ring forging, the type is taken as input and the actual working time of the sample mandrel corresponding to the type is taken as output, and the neural network is trained to obtain the mandrel prediction model, which is used to output the predicted working time of the mandrel according to the type of aviation ring forging input.

3. The method according to claim 1, wherein when the ring rolling equipment performs ring rolling on the aviation ring forgings, a ring rolling gap exists between two adjacent aviation ring forgings; The sending of fault warning information to the mandrel according to the predicted fracture time includes: Determine whether the moment when the ring rolling of the target type of aviation ring forging ends is after the predicted fracture time; When the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time, sending first fault warning information to the mandrel, the first fault warning information is used to prompt the user to replace the mandrel during the ring rolling gap before the predicted fracture time; When the target type of aviation ring forging finishes ring rolling and before the predicted fracture time, a second fault warning message to the mandrel is sent, and the second fault warning message is used to remind the user of the remaining working time of the mandrel.

4. The method according to claim 3, wherein the first fault warning information is specifically used to prompt the user to replace the mandrel at the Kth last ring rolling gap before the predicted fracture time, where K is an integer greater than 1; in, The shorter the predicted working time of the mandrel is, the larger the value of K is.

5. The method according to any one of claims 1 to 4, wherein determining the predicted fracture time of the mandrel according to the remaining working time comprises: Obtaining the duration of the ring rolling gap of the target type of aviation ring forging and the ring rolling duration of each of the target type of aviation ring forging; The predicted breaking time of the mandrel is determined according to the current time, the duration of the ring rolling gap, the ring rolling time, and the remaining working time.

6. The method according to any one of claims 1 to 4, wherein determining the remaining working time of the mandrel according to the predicted working time and the working time of the mandrel comprises: Determine the remaining working time of the spindle according to the predicted working time, a preset coefficient, and the working time of the spindle, wherein the preset coefficient is greater than 0 and less than 1; Among them, the smaller the predicted working time of the core shaft is, the smaller the value of the preset coefficient is.

7. The method according to any one of claims 1 to 4, wherein the target type comprises at least one of the following: a nickel-based high-temperature alloy type, a titanium alloy type, a steel type, an aluminum alloy type, and a blade alloy type.

8. An intelligent early warning device for ring rolling mill tooling failure, the device comprising: An acquisition unit, used for acquiring a target type of an aviation ring forging ring-rolled by a ring rolling device; An output unit, used for inputting the target type into a mandrel prediction model, and outputting the predicted working time of the mandrel of the ring rolling equipment through the mandrel prediction model, wherein the mandrel prediction model includes an input layer, an embedding layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer; a determination unit, configured to determine a remaining working time of the spindle according to the predicted working time and the working time of the spindle; The determining unit is further used to determine the predicted breaking time of the mandrel according to the remaining working time; a sending unit, configured to send fault warning information of the mandrel according to the predicted fracture time, wherein the fault warning information is used to prompt a user to replace the mandrel; The output unit is specifically used for: Determine a target type identifier corresponding to the target type; Input the target type identifier into the mandrel prediction model, convert the target type identifier into a vector through the embedding layer of the mandrel prediction model and output it; Using a convolution kernel through the convolution layer of the mandrel prediction model, convolve the vector of the target type identifier output by the embedding layer to obtain and output local features in the target type identifier; The local features in the target type identification output by the convolution layer are converted into a one-dimensional vector through the pooling layer of the mandrel prediction model, and connected to the fully connected layer; Learning the relationship between the target type identifier and the predicted working time of the mandrel through the fully connected layer of the mandrel prediction model; The output layer of the mandrel prediction model outputs the predicted working time of the mandrel when the ring rolling equipment performs ring rolling on the aviation ring forging of the target type corresponding to the target type identifier based on the relationship between the target type identifier and the predicted working time of the mandrel.

9. The device according to claim 8, further comprising: an acquisition unit, for acquiring sample data corresponding to at least two types of aviation ring forgings, respectively, wherein the sample data corresponding to each type of aviation ring forgings includes: an actual working time of each sample mandrel of the ring rolling equipment when the ring rolling equipment performs ring rolling on the aviation ring forgings of the type within a preset historical period; A training unit is used for training a neural network for sample data corresponding to each type of aviation ring forging, taking the type as input and the actual working time of the sample mandrel corresponding to the type as output, to obtain the mandrel prediction model, wherein the mandrel prediction model is used to output the predicted working time of the mandrel according to the input type of aviation ring forging.

10. The device according to claim 8, wherein when the ring rolling equipment performs ring rolling on the aviation ring forgings, a ring rolling gap exists between two adjacent aviation ring forgings; and the sending unit is specifically used for: Determine whether the moment when the ring rolling of the target type of aviation ring forging ends is after the predicted fracture time; When the moment when the target type of aviation ring forging finishes ring rolling is after the predicted fracture time, sending first fault warning information to the mandrel, the first fault warning information is used to prompt the user to replace the mandrel during the ring rolling gap before the predicted fracture time; When the target type of aviation ring forging finishes ring rolling and before the predicted fracture time, a second fault warning message to the mandrel is sent, and the second fault warning message is used to remind the user of the remaining working time of the mandrel.

11. The device according to claim 10, wherein the first fault warning information is specifically used to prompt the user to replace the mandrel at the Kth last ring rolling gap before the predicted fracture time, wherein K is an integer greater than 1; in, The shorter the predicted working time of the mandrel is, the larger the value of K is.

12. The apparatus according to any one of claims 8 to 11, wherein the determining unit is specifically configured to: Obtaining the duration of the ring rolling gap of the target type of aviation ring forging and the ring rolling duration of each of the target type of aviation ring forging; The predicted breaking time of the mandrel is determined according to the current time, the duration of the ring rolling gap, the ring rolling time, and the remaining working time.

13. The apparatus according to any one of claims 8 to 11, wherein the determining unit is specifically configured to: Determine the remaining working time of the spindle according to the predicted working time, a preset coefficient, and the working time of the spindle, wherein the preset coefficient is greater than 0 and less than 1; in, The shorter the predicted working time of the spindle is, the smaller the value of the preset coefficient is.

14. The device according to any one of claims 8 to 11, wherein the target type comprises at least one of the following: a nickel-based high-temperature alloy type, a titanium alloy type, a steel type, an aluminum alloy type, and a blade alloy type.

15. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; 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 so that the at least one processor can execute the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

17. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images