A workpiece temperature prediction method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for predicting the temperature of a workpiece. The method includes: obtaining the heating environment parameter information at the current moment when a target workpiece is heated by a high-temperature superconducting induction heating device; determining the temperature target value of the target workpiece at the last moment based on whether there is a measurement operation of the temperature sensor at the last moment; inputting the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into a temperature prediction model for temperature prediction; obtaining the temperature prediction value and the current hidden state of the target workpiece at the current moment based on the output of the temperature prediction model. Through the technical solution of the embodiment of the present invention, accurate prediction of the workpiece temperature is achieved in real time, the influence of the temperature sensor misalignment on the workpiece temperature measurement accuracy is reduced, the workpiece temperature can be made to meet the process temperature, and the quality and performance of the product can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a workpiece temperature prediction method, device, equipment and storage medium. Background Art

[0002] With the continuous development of superconducting technology, high-temperature superconducting materials have gradually been studied and applied. When using high-temperature superconducting induction heating equipment to heat a workpiece, real-time monitoring of the workpiece temperature is a very important part of the high-temperature superconducting induction heating process.

[0003] At present, the traditional method of monitoring the temperature of workpieces is to use temperature sensors, such as thermocouples, to measure the temperature of the workpiece ends. However, as the thermocouples are in long-term contact with the high-temperature workpieces, their surfaces will be contaminated, resulting in increased measurement errors. Since the thermocouples are located in a strong magnetic field environment, it is impossible to frequently clean and maintain the thermocouples in actual production. The temperature measurement error will cause the workpiece temperature to deviate from the process temperature, and the quality and performance of the product cannot be guaranteed. Summary of the invention

[0004] The present invention provides a workpiece temperature prediction method, device, equipment and storage medium to achieve real-time accurate prediction of workpiece temperature, reduce the impact of temperature sensor misalignment on workpiece temperature measurement accuracy, make the workpiece temperature meet the process temperature, and ensure product quality and performance.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting workpiece temperature, comprising:

[0006] When a target workpiece is heated by a high-temperature superconducting induction heating device, the heating environment parameter information at the current moment is obtained;

[0007] Determining a target temperature value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment;

[0008] Inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into the temperature prediction model to perform temperature prediction;

[0009] Based on the output of the temperature prediction model, a temperature prediction value and a current latent state of the target workpiece at a current moment are obtained.

[0010] In a second aspect, an embodiment of the present invention further provides a workpiece temperature prediction device, comprising:

[0011] A current parameter acquisition module is used to obtain the heating environment parameter information at the current moment when the target workpiece is heated by the high-temperature superconducting induction heating device;

[0012] A target temperature determination module, used to determine a target temperature value of the target workpiece at a previous moment based on whether there was a measurement operation of the temperature sensor at a previous moment;

[0013] A temperature prediction module is used to input the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state into the temperature prediction model to perform temperature prediction;

[0014] The current state determination module is used to obtain the temperature prediction value and current hidden state of the target workpiece at the current moment based on the output of the temperature prediction model.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, characterized in that the electronic device comprises: at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the workpiece temperature prediction method provided by any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute the workpiece temperature prediction method provided by any embodiment of the present invention when executing.

[0019] The technical solution of the embodiment of the present invention is to obtain the heating environment parameter information at the current moment during the process of heating the target workpiece using a high-temperature superconducting induction heating device. Based on whether there was a measurement operation of the temperature sensor at the last moment, the temperature target value of the target workpiece at the last moment is determined, thereby reducing the impact of the measurement error on the workpiece temperature prediction. The heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state are input into the temperature prediction model for temperature prediction, and based on the output of the temperature prediction model, the temperature prediction value and the current hidden state of the target workpiece at the current moment are obtained, thereby realizing real-time accurate prediction of the workpiece temperature by using the temperature prediction model, reducing the impact of the temperature sensor misalignment on the workpiece temperature prediction accuracy, and making the workpiece temperature meet the process temperature, ensuring the quality and performance of the product.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a workpiece temperature prediction method provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a workpiece temperature prediction method provided according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a workpiece temperature prediction device provided according to Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device for implementing the workpiece temperature prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "target", "current", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1A flowchart of a workpiece temperature prediction method is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the workpiece temperature is detected. Figure 1 As shown, the method can be performed by a workpiece temperature prediction device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method specifically comprises the following steps:

[0030] S110. When heating a target workpiece using a high-temperature superconducting induction heating device, obtain heating environment parameter information at a current moment.

[0031] Among them, the high-temperature superconducting induction heating equipment may refer to a device that uses the principle of electromagnetic induction to heat the target workpiece. The working principle of the high-temperature superconducting induction heating equipment is to generate a strong DC magnetic field under DC excitation through a superconducting magnet, and the motor drives the metal (which can be copper or aluminum) rod-shaped workpiece to rotate in the magnetic field. The workpiece forms eddy currents inside by cutting the magnetic flux lines, thereby generating Joule heat to heat the workpiece. The target workpiece may refer to the workpiece heated by the high-temperature superconducting induction heating equipment at the current moment. For example, the target workpiece may be a rod-shaped metal material (such as a copper rod, an aluminum rod, etc.). The heating environment parameter information at the current moment may refer to the motor output power, motor output torque, motor speed, excitation current and excitation voltage in the high-temperature superconducting induction heating equipment.

[0032] Specifically, the heating environment parameters that need to be monitored are determined according to the requirements of the heating process and the characteristics of the target workpiece. When the target workpiece is heated using the high-temperature superconducting induction heating device, the real-time data collected by each sensor on the high-temperature superconducting induction heating device is obtained. The collected real-time data is processed and analyzed to obtain the heating environment parameter information at the current moment, so as to better predict the workpiece temperature in the high-temperature superconducting induction heating device and optimize the heat treatment process.

[0033] S120 . Determine a target temperature value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment.

[0034] The temperature sensor may refer to a device for measuring temperature, which can convert temperature into a measurable electrical signal or chemical signal. For example, the temperature sensor may be a thermocouple, a thermistor, an infrared temperature sensor, etc. The temperature target value may refer to the actual process temperature reached by the target workpiece at the last moment.

[0035] Specifically, it is determined whether there is a measurement operation of the temperature sensor at the last moment. If there is a measurement operation of the temperature sensor at the last moment, the temperature of the workpiece measured by the temperature sensor at the last moment is compared with the temperature prediction value of the workpiece at the last moment. Based on the comparison result, the measurement error of the temperature sensor at the last moment is determined. Based on the measurement error of the temperature sensor at the last moment, the measured temperature of the temperature sensor and the temperature prediction value of the workpiece are weighted summed, and the sum result is determined as the temperature target value of the target workpiece at the last moment. If there is no measurement operation of the temperature sensor at the last moment, the temperature prediction value of the workpiece at the last moment is determined as the temperature target value of the target workpiece at the last moment. By determining the temperature target value by determining whether there is a measurement operation of the temperature sensor at the last moment, the prediction error caused by the misalignment of the temperature sensor can be reduced in real time, ensuring that the workpiece heating process meets the process temperature requirements of the workpiece in real time, and improving product quality.

[0036] S130, inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the previous moment, and the previous hidden state into the temperature prediction model to perform temperature prediction.

[0037] Among them, the size information of the target workpiece may refer to the length of the workpiece, the radius of the workpiece, etc. The hidden state may refer to a state that cannot be directly observed or measured in certain specific systems. The last hidden state may refer to the internal state information of the target workpiece that cannot be directly measured by the sensor during the heating process at the last moment. The temperature prediction model may refer to a mathematical model for predicting the temperature change of the target workpiece under given heating environment parameters, including a hidden state transfer submodel and an observation submodel. The hidden state transfer submodel may refer to a mathematical model for predicting the change of the internal state of the target workpiece during the heating process. The observation submodel may refer to a mathematical model for converting the internal state of the target workpiece during the heating process into an external temperature value.

[0038] Specifically, the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the previous moment, and the previous hidden state collected in real time are input into a pre-trained temperature prediction model for temperature prediction, thereby reducing the impact of temperature sensor inaccuracy on workpiece heating.

[0039] Exemplarily, S130 may include: inputting the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the previous moment, and the previous hidden state into the hidden state transfer sub-model for hidden state prediction, and determining the current hidden state of the target workpiece at the current moment; inputting the current hidden state into the observation sub-model for temperature prediction, and determining the predicted temperature value of the target workpiece at the current moment.

[0040] The current hidden state may refer to the internal state information of the target workpiece that cannot be directly measured by the sensor during the heating process at the current moment. The temperature prediction value at the current moment may refer to the predicted heating temperature of the target workpiece at the current moment.

[0041] Specifically, the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the previous moment, and the previous hidden state collected in real time are input into the pre-trained hidden state transfer sub-model for hidden state prediction. Based on the output of the hidden state transfer sub-model, the current hidden state of the target workpiece at the current moment is determined. The current hidden state is input into the pre-trained observation sub-model for temperature prediction, and based on the output of the observation sub-model, the temperature prediction value of the target workpiece at the current moment is determined.

[0042] S140. Based on the output of the temperature prediction model, obtain the temperature prediction value and current hidden state of the target workpiece at the current moment.

[0043] The temperature prediction value at the current moment may refer to the heating temperature of the workpiece predicted at the current moment.

[0044] Specifically, based on the output of the hidden state transfer sub-model, the current hidden state of the target workpiece at the current moment is obtained. By inputting the current hidden state into the observation sub-model, the observation sub-model converts the current hidden state into an observable external temperature value, and predicts the temperature prediction value of the target workpiece at the current moment, thereby realizing real-time and accurate prediction of the workpiece temperature.

[0045] The technical solution of the embodiment of the present invention is to obtain the heating environment parameter information at the current moment during the process of heating the target workpiece using a high-temperature superconducting induction heating device. Based on whether there was a measurement operation of the temperature sensor at the last moment, the temperature target value of the target workpiece at the last moment is determined, thereby reducing the influence of the measurement error on the workpiece temperature prediction. The heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state are input into the temperature prediction model for temperature prediction, and based on the output of the temperature prediction model, the temperature prediction value and the current hidden state of the target workpiece at the current moment are obtained, thereby realizing accurate prediction of the workpiece temperature in real time by using the temperature prediction model, reducing the influence of the temperature sensor misalignment on the workpiece temperature prediction accuracy, and making the workpiece temperature meet the process temperature, thereby ensuring the quality and performance of the product.

[0046] On the basis of the above scheme, the temperature prediction model is obtained by forced teaching training based on historical heating data; the hidden state transfer submodel is a nonlinear network model, and the observation submodel is a linear network model. Among them, forced teaching training is a supervised learning method. The model must meet these conditions by adding specific constraints during the training process. In the training process of the temperature prediction model, forced teaching refers to using known and labeled historical heating data to train the model so that the model can learn how to predict the internal state changes and temperature values ​​of the target workpiece based on the input heating environment parameter information and workpiece state information. The process of obtaining the temperature prediction model through forced teaching training is as follows:

[0047] 1. Data collection and organization: First, collect historical heating process data. Each heating process data constitutes a multivariate time series. Each moment of the time series includes the size information, temperature and heating environment parameter information of the workpiece. Therefore, a historical heating data has the following form:

[0048] X=(X0,X1,...,X T )

[0049] Among them, X K is the vector containing the above variables at the Kth moment, and the length of the sequence is T+1.

[0050] 2. Establish a hidden state transfer sub-model: The hidden state transfer sub-model can use a nonlinear network model, such as a deep neural network (DNN). This model is used to predict the internal state changes of the target workpiece based on historical data and current environmental parameters. During the training process, the historical heating data is input into the model, and by adjusting the model parameters, the model can predict the internal state changes of the target workpiece based on the input heating environment parameter information and workpiece state information. The representation of the hidden state transfer model has the following form:

[0051] Z K+1 =F θ (Z K ,Y K ,U K+1 ,C)

[0052] Among them, Z represents the hidden state of the system, Y is the system output, that is, the temperature of the target workpiece, U is the heating environment parameter information (including motor output power and other parameters). C is the fixed parameters such as the size information of the workpiece. For example: F θ It can be a nonlinear model, F θ The nonlinear activation function in is the hyperbolic tangent activation function (tanh). Then the hidden state transfer submodel is implemented using a neural network as follows:

[0053] Z K+1=tanh(W zz Z K +W yz Y K +W uz U K+1 +W cz C+b h )

[0054] Among them, W zz , W yz , W uz , W cz is the weight parameter of the network, b h is the bias parameter.

[0055] 3. Establish an observation sub-model: The observation sub-model can use a linear network model, such as linear regression. This model is used to convert the internal state of the workpiece into an observable external temperature value. During the training process, the historical heating data is input into the model, and by adjusting the model parameters, the model can estimate the corresponding external temperature value based on the input workpiece internal state information. The representation of the observation sub-model has the following form:

[0056] Y K =G φ (Z K )

[0057] Among them, Y is the temperature of the target workpiece, and Z represents the hidden state of the system. It can be a linear function, and the observation sub-model is implemented using a neural network as follows:

[0058] Y K =W zy Z K +b y

[0059] Among them, W zy is the weight parameter of the network, b y is the bias parameter, Y K is the actual temperature value at time K.

[0060] 3. Training and optimization: During the training phase, the hidden state transfer sub-model and the observation sub-model are jointly trained. By iteratively updating the model parameters, the prediction performance of the hidden state transfer sub-model and the observation sub-model is continuously optimized. Optimization algorithms such as Stochastic Gradient Descent (SGD) can be used to adjust the model parameters to minimize the error between the model's prediction results and the actual measured values. At the same time, cross-validation and other techniques can be used to prevent overfitting and improve the generalization ability of the model. The specific training process is as follows: For each heating process sequence data with a length of T+1, initialize the hidden state and set Z0=0; at any time K, according to the historical real data and the hidden state Z at the previous moment K-1 , use the hidden state transition submodel to calculate Z K , and obtain the hidden state sequence (Z1, ..., Z T ); Based on the observation sub-model G φ , calculate the predicted sequence (N1, ..., N T ) and the mean square error is used as the loss function. The SGD algorithm is used to train the model on the training set.

[0061] Embodiment 2

[0062] Figure 2 This is a flow chart of a workpiece temperature prediction method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the step of "determining the temperature target value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment". The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here.

[0063] See also Figure 2 Another workpiece temperature prediction method provided in this embodiment specifically includes the following steps:

[0064] S210. When heating a target workpiece using a high-temperature superconducting induction heating device, obtain heating environment parameter information at a current moment.

[0065] S220: If there is a measurement operation of the temperature sensor at the last moment, determine the temperature target value of the target workpiece at the last moment based on the temperature measurement value at the last moment.

[0066] Specifically, since the temperature sensor may not measure the temperature accurately due to long-term use, when the temperature sensor has not yet had serious measurement errors, it is necessary to determine the workpiece temperature by combining the temperature sensor with the temperature prediction model to further improve the accuracy of the workpiece temperature determination. If there was a measurement operation of the temperature sensor at the last moment, the workpiece temperature measured by the temperature sensor at the last moment and the temperature prediction value of the workpiece at the last moment are weighted and summed, and the result of the weighted sum is determined as the target temperature value of the target workpiece at the last moment, thereby reducing the impact of the measurement error of the temperature sensor.

[0067] Exemplarily, "determining the temperature target value of the target workpiece at the last moment based on the temperature measurement value at the last moment" in S220 may include: weighting the temperature measurement value at the last moment and the temperature prediction value at the last moment to determine the temperature target value of the target workpiece at the last moment.

[0068] Specifically, if there is a measurement operation of the temperature sensor at the last moment, determine whether the last moment is the initial moment of heating the target workpiece. If the last moment is the initial moment of heating the target workpiece, it indicates that there is no temperature prediction value at the last moment. At this time, the current room temperature can be directly determined as the temperature prediction value of the target workpiece at the last moment, and the temperature measurement value at the last moment and the temperature prediction value of the target workpiece at the last moment are weighted and summed, and the sum result is determined as the temperature target value of the target workpiece at the last moment, or the temperature measurement value at the last moment can be directly determined as the temperature target value of the target workpiece at the last moment. If the last moment is a subsequent moment of the initial moment of heating the target workpiece, the workpiece temperature measured by the temperature sensor at the last moment and the temperature prediction value of the workpiece at the last moment are weighted and summed, and the sum result is determined as the temperature target value of the target workpiece at the last moment, thereby reducing the influence of the measurement error of the temperature sensor on the temperature prediction. It should be noted that the sum weight between the workpiece temperature measured by the temperature sensor at the last moment and the temperature prediction value of the workpiece at the last moment is determined in advance based on the business scenario and actual needs.

[0069] It should be noted that, with the long-term use of the temperature sensor, when the measurement error of the temperature sensor is large, the temperature prediction value of the target workpiece at the last moment is directly determined as the temperature target value.

[0070] S230: If there is no measurement operation of the temperature sensor at the last moment, determine the temperature prediction value of the target workpiece at the last moment as the temperature target value.

[0071] Specifically, when the temperature sensor of the heating equipment has a serious measurement error or is unavailable, the temperature prediction model is used to iteratively predict the temperature to reduce the impact of the temperature sensor misalignment on the heating of the workpiece. If there is no measurement operation of the temperature sensor at the last moment, it is determined whether the current moment is the initial moment of heating the target workpiece. If the current moment is the initial moment of heating the target workpiece, the room temperature at the current moment is used as the temperature target value of the target workpiece at the last moment. If the current moment is a subsequent moment of the initial moment, the temperature prediction value of the target workpiece at the last moment is determined as the temperature target value. There is no need for the measurement operation of the temperature sensor, which alleviates the problem of difficult maintenance of the temperature sensor in the high-temperature superconducting induction heating equipment.

[0072] Exemplarily, "determining the temperature prediction value of the target workpiece at the last moment as the temperature target value" in S230 may include: if the current moment is the initial heating moment, determining the current room temperature as the temperature target value of the target workpiece at the last moment; if the current moment is the subsequent heating moment after the initial heating moment, determining the temperature prediction value of the target workpiece at the last moment as the temperature target value.

[0073] Specifically, if the current moment is the initial heating moment, the target workpiece temperature at this time is usually close to room temperature. Therefore, using the current room temperature as the temperature target value can provide the operator with a reasonable starting point to start the heating process, so the room temperature at the current moment is determined as the temperature target value of the target workpiece at the last moment. If the current moment is a subsequent heating moment after the initial heating moment, that is, the heating process has started for a while, then the temperature prediction model can be used to predict the temperature of the target workpiece at the last moment, and the temperature prediction value of the target workpiece at the last moment can be determined as the temperature target value. Using room temperature as the temperature target value at the initial heating moment can simplify the operation and provide a reasonable starting point; and at the subsequent heating moment, the use of the temperature prediction model can provide better predictability and accuracy, ensuring that the workpiece temperature meets the process temperature requirements in real time and achieving a stable heating process.

[0074] S240, inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state into the temperature prediction model to perform temperature prediction.

[0075] S250. Based on the output of the temperature prediction model, obtain the temperature prediction value and current hidden state of the target workpiece at the current moment.

[0076] The technical solution of the embodiment of the present invention is as follows: if there is a measurement operation of the temperature sensor at the last moment, then the temperature target value of the target workpiece at the last moment is determined based on the temperature measurement value at the last moment; if there is no measurement operation of the temperature sensor at the last moment, then the temperature prediction value of the target workpiece at the last moment is determined as the temperature target value, thereby further improving the accuracy of the workpiece temperature prediction, and then achieving the accuracy of the workpiece temperature control, ensuring in real time that the workpiece temperature meets the process temperature requirements, and realizing a stable heating process.

[0077] Embodiment 3

[0078] Figure 3 This is a schematic diagram of the structure of a workpiece temperature prediction device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a current parameter acquisition module 310, a target temperature determination module 320, a temperature prediction module 330 and a current state determination module 340.

[0079] The current parameter acquisition module 310 is used to acquire the heating environment parameter information at the current moment during the process of heating the target workpiece using the high temperature superconducting induction heating device;

[0080] A target temperature determination module 320 is used to determine a target temperature value of the target workpiece at a previous moment based on whether there was a measurement operation of the temperature sensor at a previous moment;

[0081] The temperature prediction module 330 is used to input the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into the temperature prediction model to perform temperature prediction;

[0082] The current state determination module 340 is used to obtain the temperature prediction value and the current hidden state of the target workpiece at the current moment based on the output of the temperature prediction model.

[0083] The technical solution of this embodiment is to obtain the heating environment parameter information at the current moment during the process of heating the target workpiece using a high-temperature superconducting induction heating device. Based on whether there was a measurement operation of the temperature sensor at the last moment, the temperature target value of the target workpiece at the last moment is determined, thereby reducing the impact caused by the measurement error. The heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state are input into the temperature prediction model for temperature prediction, and based on the output of the temperature prediction model, the temperature prediction value and current hidden state of the target workpiece at the current moment are obtained, thereby realizing real-time accurate prediction of the workpiece temperature, reducing the impact of temperature sensor inaccuracy on the accuracy of workpiece temperature prediction, and making the workpiece temperature meet the process temperature, ensuring the quality and performance of the product.

[0084] Optionally, the heating environment parameter information includes: motor output power, motor output torque, motor speed, excitation current and excitation voltage in the high-temperature superconducting induction heating equipment.

[0085] Optionally, the target temperature determination module 310 includes:

[0086] a first temperature determination unit, configured to determine a target temperature value of the target workpiece at a previous moment based on a temperature measurement value at a previous moment if there was a measurement operation of the temperature sensor at a previous moment;

[0087] The second temperature determination unit is configured to determine the predicted temperature value of the target workpiece at the last moment as the temperature target value if there is no measurement operation of the temperature sensor at the last moment.

[0088] Optionally, the first temperature determination unit is specifically configured to: perform weighted processing on the temperature measurement value at the last moment and the temperature prediction value at the last moment to determine the temperature target value of the target workpiece at the last moment.

[0089] Optionally, the second temperature determination unit is specifically used to: if the current moment is the initial heating moment, determine the current room temperature as the temperature target value of the target workpiece at the previous moment; if the current moment is the subsequent heating moment after the initial heating moment, determine the temperature prediction value of the target workpiece at the previous moment as the temperature target value.

[0090] Optionally, the temperature prediction model includes: a hidden state transfer submodel and an observation submodel; a temperature prediction module, specifically used to: input the heating environment parameter information at the current moment, the size information of the target workpiece, and the temperature target value and the previous hidden state at the previous moment into the hidden state transfer submodel for hidden state prediction, and determine the current hidden state of the target workpiece at the current moment; input the current hidden state into the observation submodel for temperature prediction, and determine the predicted temperature value of the target workpiece at the current moment.

[0091] Optionally, the temperature prediction model is obtained by forced teaching and training based on historical heating data; the hidden state transfer sub-model is a nonlinear network model, and the observation sub-model is a linear network model.

[0092] The workpiece temperature prediction device provided in the embodiment of the present invention can execute the workpiece temperature prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] Figure 4A schematic diagram of the structure of an electronic device 12 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as desktop computers, workstations, servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, smart phones, wearable devices (such as helmets, glasses, watches, etc.) 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 invention described and / or required herein.

[0094] like Figure 4 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0095] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0096] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0097] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0098] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0099] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0100] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a workpiece temperature prediction method provided by the embodiment of the present invention, the method comprising:

[0101] When a target workpiece is heated by a high-temperature superconducting induction heating device, the heating environment parameter information at the current moment is obtained;

[0102] Determining a target temperature value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment;

[0103] Inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into the temperature prediction model to perform temperature prediction;

[0104] Based on the output of the temperature prediction model, a temperature prediction value and a current latent state of the target workpiece at a current moment are obtained.

[0105] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the workpiece temperature prediction method provided by any embodiment of the present invention.

[0106] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the workpiece temperature prediction method provided in any embodiment of the present invention are implemented. The method includes:

[0107] When a target workpiece is heated by a high-temperature superconducting induction heating device, the heating environment parameter information at the current moment is obtained;

[0108] Determining a target temperature value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment;

[0109] Inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into the temperature prediction model to perform temperature prediction;

[0110] Based on the output of the temperature prediction model, a temperature prediction value and a current latent state of the target workpiece at a current moment are obtained.

[0111] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0112] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0113] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0114] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0115] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0116] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for predicting workpiece temperature, characterized in that: include: When a target workpiece is heated by a high-temperature superconducting induction heating device, the heating environment parameter information at the current moment is obtained; Determining a target temperature value of the target workpiece at the last moment based on whether there was a measurement operation of the temperature sensor at the last moment; Inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment and the last hidden state into the temperature prediction model to perform temperature prediction; Based on the output of the temperature prediction model, obtaining a temperature prediction value and a current hidden state of the target workpiece at a current moment; The step of determining the target temperature value of the target workpiece at the last moment based on whether there is a measurement operation of the temperature sensor at the last moment comprises: If there is a measurement operation of the temperature sensor at the last moment, then based on the temperature measurement value at the last moment, determining the temperature target value of the target workpiece at the last moment; If there is no measurement operation of the temperature sensor at the last moment, the predicted temperature value of the target workpiece at the last moment is determined as the temperature target value.

2. The method according to claim 1, characterized in that The heating environment parameter information includes: motor output power, motor output torque, motor speed, excitation current and excitation voltage in the high-temperature superconducting induction heating equipment.

3. The method according to claim 1, characterized in that Determining a target temperature value of the target workpiece at the last moment based on the temperature measurement value at the last moment includes: The temperature measurement value at the last moment and the temperature prediction value at the last moment are weighted to determine the temperature target value of the target workpiece at the last moment.

4. The method according to claim 1, characterized in that Determining the temperature prediction value of the target workpiece at the last moment as the temperature target value includes: If the current moment is the initial heating moment, the current room temperature is determined as the temperature target value of the target workpiece at the previous moment; If the current moment is a subsequent heating moment after the initial heating moment, the temperature prediction value of the target workpiece at the previous moment is determined as the temperature target value.

5. The method according to claim 1, characterized in that The temperature prediction model includes: a hidden state transfer sub-model and an observation sub-model; The step of inputting the current heating environment parameter information, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state into the temperature prediction model for temperature prediction includes: Inputting the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the previous moment, and the previous hidden state into the hidden state transfer sub-model to perform hidden state prediction, and determine the current hidden state of the target workpiece at the current moment; The current hidden state is input into the observation sub-model to perform temperature prediction, and the predicted temperature value of the target workpiece at the current moment is determined.

6. The method according to claim 5, characterized in that The temperature prediction model is obtained by forced teaching training based on historical heating data, wherein forced teaching refers to using known and labeled historical heating data to train the model; The hidden state transfer sub-model is a nonlinear network model, and the observation sub-model is a linear network model.

7. A workpiece temperature prediction device, characterized in that: include: A current parameter acquisition module is used to obtain the heating environment parameter information at the current moment when the target workpiece is heated by the high-temperature superconducting induction heating device; A target temperature determination module, used to determine a target temperature value of the target workpiece at a previous moment based on whether there was a measurement operation of the temperature sensor at a previous moment; A temperature prediction module is used to input the heating environment parameter information at the current moment, the size information of the target workpiece, the temperature target value at the last moment, and the last hidden state into the temperature prediction model to perform temperature prediction; A current state determination module, used to obtain a temperature prediction value and a current hidden state of the target workpiece at a current moment based on the output of the temperature prediction model; The target temperature determination module comprises: a first temperature determination unit, configured to determine a target temperature value of the target workpiece at a previous moment based on a temperature measurement value at a previous moment if there was a measurement operation of the temperature sensor at a previous moment; The second temperature determination unit is configured to determine the predicted temperature value of the target workpiece at the last moment as the temperature target value if there is no measurement operation of the temperature sensor at the last moment.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the workpiece temperature prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the workpiece temperature prediction method according to any one of claims 1 to 6 when executed.

Images