Artificial Intelligence-based Washing Machine Valve Production Management System and Method

Abstract

The present disclosure relates to a production management system and method for a washing machine valve based on artificial intelligence. The method includes: performing domain transformation on the acquired device vibration signal to obtain a device vibration time-frequency image; performing vibration correlation pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors; inputting the sequence of context device vibration local time-frequency semantic representation vectors into a significance enhancement fusion module based on sequence distribution cluster centers to obtain a global device vibration time-frequency representation vector; and determining a management result based on the global device vibration time-frequency representation vector. In this way, the detection and recognition of abnormal working states of washing machine valve production equipment can be realized, and the service life of the washing machine and the user experience can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent manufacturing technology, and more particularly, to a washing machine valve production management system and method based on artificial intelligence. Background Art

[0002] With the development of industry, intelligent manufacturing has become an important direction for the development of the manufacturing industry. In this context, traditional production methods are gradually being replaced by intelligent and automated systems. As a key component in household appliances, the efficiency and quality of the production process of washing machine valves directly affect the performance and reliability of the final product. However, traditional production monitoring methods often rely on manual inspection, which is not only inefficient but also easily interfered by human factors, resulting in inaccurate inspection results.

[0003] To improve the automation level and quality control ability of washing machine valve production management, a washing machine valve production management system and method based on artificial intelligence are expected. Summary of the Invention

[0004] This Summary of the Invention section is provided to introduce concepts in a brief form that will be described in detail in the following Detailed Description section. This Summary of the Invention section is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a washing machine valve production management method based on artificial intelligence, the method comprising:

[0006] Obtaining device vibration signals collected by vibration sensors deployed on washing machine valve production equipment;

[0007] Performing domain transformation on the device vibration signals to obtain a device vibration time-frequency image;

[0008] Performing vibration correlation pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors;

[0009] Inputting the sequence of context device vibration local time-frequency semantic representation vectors into a significance enhancement fusion module based on sequence distribution cluster centers to obtain a global device vibration time-frequency representation vector;

[0010] Determining a management result based on the global device vibration time-frequency representation vector.

[0011] Optionally, performing domain transformation on the device vibration signals to obtain a device vibration time-frequency image includes: performing wavelet transformation on the device vibration signals to obtain the device vibration time-frequency image.

[0012] Optionally, perform vibration correlation pattern analysis on the time-frequency image of the device vibration to obtain a sequence of context device vibration local time-frequency semantic representation vectors, including: performing image block processing on the time-frequency image of the device vibration to obtain a sequence of local time-frequency images of the device vibration; passing the sequence of local time-frequency images of the device vibration through a transformer structure including an image block embedding layer to obtain the sequence of context device vibration local time-frequency semantic representation vectors.

[0013] Optionally, passing the sequence of local time-frequency images of the device vibration through a transformer structure including an image block embedding layer to obtain the sequence of context device vibration local time-frequency semantic representation vectors, including: passing the sequence of local time-frequency images of the device vibration through the image block embedding layer to obtain a sequence of local time-frequency embedding feature vectors of the device vibration; passing the sequence of local time-frequency embedding feature vectors of the device vibration through the transformer structure to obtain the sequence of context device vibration local time-frequency semantic representation vectors.

[0014] Optionally, inputting the sequence of context device vibration local time-frequency semantic representation vectors into a saliency reinforcement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector, including: calculating the mean vector of the sequence of context device vibration local time-frequency semantic representation vectors as the sequence distribution cluster center; calculating the semantic correlation degree between each context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors and the sequence distribution cluster center to obtain a sequence of semantic correlation degrees; performing normalization processing on the sequence of semantic correlation degrees to obtain a sequence of device vibration local saliency correlation intensity factors; using the sequence of device vibration local saliency correlation intensity factors as a weight sequence, and calculating the vector-by-vector weighted sum of the sequence of context device vibration local time-frequency semantic representation vectors to obtain the global device vibration time-frequency representation vector.

[0015] Optionally, calculating the semantic correlation degree between each context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors and the sequence distribution cluster center to obtain a sequence of semantic correlation degrees, including: passing each context device vibration local time-frequency semantic representation vector through a fully connected layer to obtain a sequence of context device vibration local time-frequency semantic fully connected encoded feature vectors; calculating the vector multiplication of the transposed vector of the sequence distribution cluster center and each context device vibration local time-frequency semantic fully connected encoded feature vector to obtain the sequence of semantic correlation degrees.

[0016] Optionally, the fully connected layer uses the sigmoid function.

[0017] Optionally, normalizing the sequence of the semantic correlation degrees to obtain a sequence of device vibration local significance correlation strength factors, including: inputting the sequence of the semantic correlation degrees into a softmax function for soft-maximum normalization to obtain the sequence of the device vibration local significance correlation strength factors.

[0018] Optionally, determining a management result based on the global device vibration time-frequency representation vector, including: passing the global device vibration time-frequency representation vector through a management result generator based on a classifier to obtain the management result, where the management result is used to indicate whether there is an abnormality in the working state of the washing machine valve production equipment.

[0019] In a second aspect, the present disclosure provides an artificial intelligence-based washing machine valve production management system, where the system includes:

[0020] A device vibration signal acquisition module, configured to acquire a device vibration signal collected by a vibration sensor deployed on a washing machine valve production device;

[0021] A domain transformation module, configured to perform domain transformation on the device vibration signal to obtain a device vibration time-frequency image;

[0022] A vibration correlation pattern analysis module, configured to perform vibration correlation pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors;

[0023] A significance enhancement fusion module, configured to input the sequence of the context device vibration local time-frequency semantic representation vectors into a significance enhancement fusion module based on the center of a sequence distribution cluster to obtain a global device vibration time-frequency representation vector;

[0024] A management result determination module, configured to determine a management result based on the global device vibration time-frequency representation vector.

[0025] By adopting the above technical solution, a device vibration time-frequency image is obtained by performing domain transformation on the acquired device vibration signal; a sequence of context device vibration local time-frequency semantic representation vectors is obtained by performing vibration correlation pattern analysis on the device vibration time-frequency image; a global device vibration time-frequency representation vector is obtained by inputting the sequence of the context device vibration local time-frequency semantic representation vectors into a significance enhancement fusion module based on the center of a sequence distribution cluster; and a management result is determined based on the global device vibration time-frequency representation vector. In this way, the detection and recognition of the abnormal working state of the washing machine valve production device can be realized, and the service life of the washing machine and the user experience can be improved.

[0026] Other features and advantages of the present disclosure will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0027] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the elements and components are not necessarily drawn to scale. In the drawings:

[0028] Figure 1 is a flowchart of a method for managing the production of washing machine valves based on artificial intelligence according to an exemplary embodiment.

[0029] Figure 2 is a block diagram of a system for managing the production of washing machine valves based on artificial intelligence according to an exemplary embodiment.

[0030] Figure 3 is a block diagram of an electronic device according to an exemplary embodiment.

[0031] Figure 4 is an application scenario diagram of a method for managing the production of washing machine valves based on artificial intelligence according to an exemplary embodiment. Detailed Description

[0032] Embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0033] It should be understood that the various steps recited in the method embodiments of the present disclosure may be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0034] As used herein, the term "including" and its variants are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0035] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not intended to limit the order of the functions performed by these devices, modules, or units or their interdependent relationships.

[0036] It should be noted that the modification of "one" and "multiple" mentioned in this disclosure is illustrative rather than restrictive. Those skilled in the art should understand that, unless clearly specified otherwise in the context, it should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] Intelligent manufacturing is becoming a frontier trend in the manufacturing industry, and this transformation has promoted the transformation of traditional production models towards intelligence and automation. In the field of household appliances, as a core component, the manufacturing process of washing machine valves is directly related to the overall performance and durability of washing machines. However, currently, the production monitoring of washing machine valves often still relies on manual inspection. This method not only has low efficiency but is also easily affected by human errors, which may lead to inaccurate product detection.

[0039] To address this challenge, the industry is seeking an innovative solution, that is, to develop an artificial intelligence-based production management system and method for washing machine valves, which will utilize advanced algorithms and data analysis capabilities to achieve automated monitoring and management of the production process, thereby improving production efficiency and product quality. Specifically, the artificial intelligence-based production management system and method for washing machine valves will be able to: through machine vision and sensor technologies, monitor key parameters in the production process in real time, such as the size, shape, and material properties of the valves; use artificial intelligence algorithms to deeply analyze the collected data to identify possible abnormal situations in the production process; through analyzing production data, predict equipment failures and maintenance requirements, thereby reducing downtime and maintenance costs; automatically detect product defects to ensure that only valves meeting the standards can enter the next production link; optimize the production process and resource allocation based on the data analysis results to improve production efficiency and reduce costs; provide real-time production reports and analysis to help management make data-based decisions.

[0040] Through this artificial intelligence-based production management system and method for washing machine valves, not only can production efficiency be improved and human errors be reduced, but also the consistency and reliability of product quality can be ensured, ultimately enhancing market competitiveness.

[0041] To solve the above problems, the present disclosure provides a production management system and method for washing machine valves based on artificial intelligence. By performing domain transformation on the acquired device vibration signals, a device vibration time-frequency image is obtained; vibration correlation pattern analysis is performed on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors; the sequence of context device vibration local time-frequency semantic representation vectors is input into a saliency enhancement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector; and a management result is determined based on the global device vibration time-frequency representation vector. In this way, the detection and identification of abnormal working states of washing machine valve production equipment can be realized, and the service life and user experience of the washing machine can be improved.

[0042] The following will describe in detail the specific embodiments of the present disclosure with reference to the accompanying drawings.

[0043] Figure 1 is a flowchart of a production management method for washing machine valves based on artificial intelligence shown according to an exemplary embodiment. As Figure 1 shown, the method includes:

[0044] Step 101, acquiring device vibration signals collected by vibration sensors deployed on washing machine valve production equipment;

[0045] Step 102, performing domain transformation on the device vibration signals to obtain a device vibration time-frequency image;

[0046] Step 103, performing vibration correlation pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors;

[0047] Step 104, inputting the sequence of context device vibration local time-frequency semantic representation vectors into a saliency enhancement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector;

[0048] Step 105, determining a management result based on the global device vibration time-frequency representation vector.

[0049] The production equipment for washing machine valves refers to the mechanical equipment and production lines used to manufacture various valves in washing machines. These valves may include inlet valves, drain valves, water level control valves, etc., which play important roles in the realization of the functions of washing machines. The quality and performance of these valves directly affect the service life of washing machines and the user experience. In order to improve the automation level and quality control ability of the production management of washing machine valves, the technical concept of this disclosure is: to use sensor technology and artificial intelligence technology to monitor and analyze abnormalities in the operation process of the production equipment for washing machine valves. More specifically, the vibration signals of the production equipment for washing machine valves are collected, the vibration correlation pattern analysis is performed on the vibration signals of the equipment, and the sequence distribution cluster center is introduced to optimize the characterization of the global vibration characteristics of the equipment, so as to realize the detection and identification of the abnormal working state of the production equipment for washing machine valves.

[0050] Based on this, in the technical solution of this disclosure, first, the equipment vibration signals collected by vibration sensors deployed on the production equipment for washing machine valves are obtained. Here, the equipment vibration signals are a direct reflection of the operating state of the production equipment for washing machine valves. In actual application scenarios, when a fault occurs in the production equipment for washing machine valves, its vibration characteristics usually change. Therefore, the equipment vibration signals are an important data basis for subsequent abnormality diagnosis.

[0051] Then, wavelet transform is performed on the equipment vibration signals to obtain the time-frequency image of the equipment vibration. Among them, wavelet transform is a mathematical transform that is usually used in the fields of signal processing and image processing. It allows the analysis of the local characteristics of signals or images at different scales or resolutions. It is worth mentioning that different from Fourier transform, wavelet transform can not only provide frequency information but also time information, which makes it particularly useful in processing non-stationary signals (the frequency characteristics of signals change with time). Since the equipment vibration signals are usually non-stationary, wavelet transform can provide both the time and frequency information of the signals, which helps to identify the instantaneous characteristics in the signals and convert the equipment vibration signals into the time-frequency image of the equipment vibration.

[0052] In an embodiment of this disclosure, performing domain transform on the equipment vibration signals to obtain the time-frequency image of the equipment vibration includes: performing wavelet transform on the equipment vibration signals to obtain the time-frequency image of the equipment vibration.

[0053] Next, perform image block processing on the time-frequency image of the device vibration to obtain a sequence of local time-frequency images of the device vibration; and pass the sequence of local time-frequency images of the device vibration through a transformer structure including an image block embedding layer to obtain a sequence of context device vibration local time-frequency semantic representation vectors. Here, through image block processing, the time-frequency image of the device vibration can be split into local image blocks, guiding the subsequent model to capture detailed information and identify local abnormal or mutation information. After that, use a transformer structure including an image block embedding layer to perform a structured embedding representation on each local time-frequency image of the device vibration, and integrate the context information of each local vibration semantic representation, so as to understand complex device vibration patterns.

[0054] In an embodiment of the present disclosure, performing vibration correlation pattern analysis on the time-frequency image of the device vibration to obtain a sequence of context device vibration local time-frequency semantic representation vectors includes: performing image block processing on the time-frequency image of the device vibration to obtain a sequence of local time-frequency images of the device vibration; passing the sequence of local time-frequency images of the device vibration through a transformer structure including an image block embedding layer to obtain the sequence of context device vibration local time-frequency semantic representation vectors.

[0055] Further, passing the sequence of local time-frequency images of the device vibration through a transformer structure including an image block embedding layer to obtain the sequence of context device vibration local time-frequency semantic representation vectors includes: passing the sequence of local time-frequency images of the device vibration through the image block embedding layer to obtain a sequence of local time-frequency embedding feature vectors of the device vibration; passing the sequence of local time-frequency embedding feature vectors of the device vibration through the transformer structure to obtain the sequence of context device vibration local time-frequency semantic representation vectors.

[0056] It should be understood that in the technical solution of the present disclosure, globally integrating the sequence of context device vibration local time-frequency semantic representation vectors can form a global vibration state feature distribution of the washing machine valve production equipment during operation. However, considering that the influence of the local time-frequency distribution characteristics of each vibration mode on the final decision may be different. For example, there may be insignificant or noise-induced feature information in the device vibration signal, and these feature information may be retained during the above vibration correlation pattern analysis, thus affecting the final judgment and decision. In addition, affected by conditional dependence and time sensitivity, different degrees of attention need to be paid to vibration patterns at different stages, so as to better understand the working state characteristics of the washing machine valve production equipment. Based on this, in the technical solution of the present disclosure, further input the sequence of context device vibration local time-frequency semantic representation vectors into a significance enhancement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector.

[0057] In an embodiment of the present disclosure, the specific encoding process of inputting the sequence of the context device vibration local time-frequency semantic representation vector into the significance enhancement fusion module based on the sequence distribution cluster center to obtain the global device vibration time-frequency representation vector includes: first, calculating the mean vector of the sequence of the context device vibration local time-frequency semantic representation vector as the sequence distribution cluster center. Here, the sequence distribution cluster center can represent the global core feature of the entire sequence. Then, each of the context device vibration local time-frequency semantic representation vectors is passed through a fully connected layer to obtain a sequence of context device vibration local time-frequency semantic fully connected encoding feature vectors. That is, the fully connected layer is used to encode each of the context device vibration local time-frequency semantic representation vectors to convert the original data into a higher-level semantic feature representation, thereby enhancing the model's ability to capture complex features. Subsequently, the semantic association between each context device vibration local time-frequency semantic representation vector in the sequence of the context device vibration local time-frequency semantic representation vector and the sequence distribution cluster center is calculated to obtain a sequence of semantic associations. Here, the semantic relevance between each context device vibration local time-frequency semantic fully connected encoding feature vector and the center of the sequence distribution cluster is quantified by multiplication operation between vectors, that is, the correlation between each local feature and the global trend. After that, the sequence of the semantic relevance is input into the softmax function for normalization based on the soft maximum value to obtain the sequence of local significant association strength factors of device vibration; and the sequence of local significant association strength factors of device vibration is used as the weight sequence to calculate the vector-by-vector weighted sum of the sequence of local time-frequency semantic representation vectors of the context device vibration to obtain the global device vibration time-frequency representation vector. Among them, each semantic relevance is normalized by applying the softmax function, and the local significant association strength factors of the device vibration obtained after normalization are weighted one by one with the local time-frequency semantic representation vector of the context device vibration, so as to highlight the feature distribution pattern most relevant to the current task, and realize the core idea of ​​the attention mechanism (i.e., giving greater weight to important features).

[0058] The fully connected layer uses a sigmoid function.

[0059] That is, in one embodiment of the present disclosure, the sequence of the context device vibration local time-frequency semantic representation vector is input into a significance enhancement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector, including: calculating the mean vector of the sequence of the context device vibration local time-frequency semantic representation vector as the sequence distribution cluster center; calculating the semantic association between each context device vibration local time-frequency semantic representation vector in the sequence of the context device vibration local time-frequency semantic representation vector and the sequence distribution cluster center to obtain a sequence of semantic associations; normalizing the sequence of semantic associations to obtain a sequence of device vibration local significance association strength factors; using the sequence of device vibration local significance association strength factors as a weight sequence, calculating the vector-by-vector weighted sum of the sequence of the context device vibration local time-frequency semantic representation vector to obtain the global device vibration time-frequency representation vector.

[0060] Furthermore, in one embodiment of the present disclosure, the semantic association between each context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors and the center of the sequence distribution cluster is calculated to obtain a sequence of semantic associations, including: passing each context device vibration local time-frequency semantic representation vector through a fully connected layer to obtain a sequence of context device vibration local time-frequency semantic fully connected encoding feature vectors; calculating the transposed vector of the center of the sequence distribution cluster and multiplying it by the vector of each context device vibration local time-frequency semantic fully connected encoding feature vector to obtain the sequence of semantic associations.

[0061] Furthermore, in one embodiment of the present disclosure, the sequence of semantic associations is normalized to obtain a sequence of local significance association strength factors of device vibrations, including: inputting the sequence of semantic associations into a softmax function for soft maximum value-based normalization to obtain a sequence of local significance association strength factors of device vibrations.

[0062] Specifically, the sequence of the local time-frequency semantic representation vector of the context device vibration is input into the significance enhancement fusion module based on the center of the sequence distribution cluster according to the following fusion formula to obtain the global device vibration time-frequency representation vector; wherein the fusion formula is:

[0063]

[0064]

[0065]

[0066] Where N is the number of local time-frequency semantic representation vectors of the context device vibration, v iis the i-th context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors, v r is the center of the sequence distribution cluster, is the transposed vector of the center of the sequence distribution cluster, sigmoid represents the sigmoid function, W i and B i are the weight matrix and bias vector of the fully connected layer respectively, e i is the i-th semantic association degree, softmax represents the softmax function, v a is the global device vibration time-frequency representation vector.

[0067] Subsequently, the global device vibration time-frequency representation vector is passed through a management result generator based on a classifier to obtain a management result, and the management result is used to indicate whether there is an abnormality in the working state of the washing machine valve production equipment.

[0068] In an embodiment of the present disclosure, determining the management result based on the global device vibration time-frequency representation vector includes: passing the global device vibration time-frequency representation vector through a management result generator based on a classifier to obtain the management result, and the management result is used to indicate whether there is an abnormality in the working state of the washing machine valve production equipment.

[0069] In a preferred embodiment, passing the global device vibration time-frequency representation vector through a management result generator based on a classifier to obtain a management result includes the following steps:

[0070] Determine the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue at any two different positions of the global device vibration time-frequency representation vector;

[0071] Determine the abnormal probability value corresponding to the abnormal working state of the washing machine valve production equipment and the normal probability value corresponding to the normal working state of the washing machine valve production equipment obtained by passing the global device vibration time-frequency representation vector through a classifier;

[0072] Divide the abnormal probability value by the normal probability value to obtain the global device vibration time-frequency relative class probability distribution value;

[0073] Multiply the risk probability value by the risk-free probability value to obtain the global device vibration time-frequency collaborative class probability distribution value;

[0074] Multiply the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue after subtracting the global device vibration time-frequency relative class probability distribution value respectively to obtain the global device vibration time-frequency relative joint representation;

[0075] Add the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue, and then divide the sum by the global device vibration time-frequency collaborative class probability distribution value to obtain the global device vibration time-frequency system response characterization;

[0076] After adding the global device vibration time-frequency relative joint characterization and the global device vibration time-frequency system response characterization, use the sum as the matrix value at the corresponding coordinates of different positions of the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue to obtain the global device vibration time-frequency correction matrix;

[0077] Calculate the inner product of each row vector of the global device vibration time-frequency correction matrix and the global device vibration time-frequency representation vector to obtain the optimized global device vibration time-frequency representation vector;

[0078] Pass the optimized global device vibration time-frequency representation vector through a classifier-based management result generator to obtain the management result.

[0079] That is, when performing global image semantic space domain local image semantic space domain image semantic feature saliency enhancement fusion on the image semantic features of the global device vibration time-frequency representation vector in the local image semantic space domain of the device vibration time-frequency image, due to the saliency enhancement differences in the image semantic distributions in different local image semantic space domains, it causes local distribution differences in the global device vibration time-frequency representation vector, affecting the classification iteration effect. The above preferred embodiment takes the eigenvalues of the global device vibration time-frequency representation vector as units, and for the relative class probability distribution form and collaborative class probability distribution form of the abnormal class probability and normal class probability obtained by the classifier for the global device vibration time-frequency representation vector as a feature set, respectively perform relative-based joint characterization and collaborative-based response characterization of eigenvalue pairs of the global device vibration time-frequency representation vector, so as to avoid class induction bias caused by local distribution differences corresponding to the eigenvalues of the global device vibration time-frequency representation vector, and establish a robust understanding paradigm for class recognition of the global device vibration time-frequency representation vector as a whole feature set, thereby improving the iteration effect of the global device vibration time-frequency representation vector as a feature set in the classification process. That is, improve the speed of classification training and the accuracy of classification results when the global device vibration time-frequency representation vector is classified by the management result generator.

[0080] In summary, adopting the above solution, by applying sensor technology and artificial intelligence technology, the operation process of the washing machine valve production equipment is monitored and abnormal analyzed. More specifically, the vibration signals of the washing machine valve production equipment are collected, and through the vibration correlation pattern analysis of the equipment's vibration signals, and the sequence distribution cluster center is introduced to optimize the characterization of the equipment's global vibration characteristics, so as to realize the detection and identification of the abnormal working state of the washing machine valve production equipment.

[0081] That is, first, by installing high-precision sensors on the washing machine valve production equipment, the operation data of the equipment, especially the vibration signals, are collected in real time. The vibration signals are important indicators of the equipment's health status and can reflect the operation status of the equipment; then, the collected vibration signals will be transmitted to the data processing system, where advanced signal processing technologies, such as fast Fourier transform (FFT) or wavelet transform, are used to analyze the signals to identify the characteristics that may indicate equipment abnormalities. Then, through in-depth analysis of the vibration signals, the correlation between the vibration patterns of the equipment in normal operation and abnormal states can be found. This pattern recognition helps to understand the potential causes of equipment failures. Then, the concept of the sequence distribution cluster center is introduced, which is a mathematical method used to characterize the global vibration characteristics of the equipment. Through this method, the vibration characteristics of the equipment in different states can be more accurately identified, thereby optimizing the characterization of the vibration characteristics. Then, combining the vibration correlation pattern analysis and the sequence distribution cluster center technology, the artificial intelligence system can monitor the operation status of the equipment in real time. Once vibration characteristics inconsistent with the normal mode are detected, it will automatically identify and issue an alarm to prompt possible equipment abnormalities.

[0082] It should be understood that this can not only detect abnormalities, but also provide decision-making support to help operators or maintenance teams respond quickly and take appropriate maintenance or repair measures to minimize the risk of production interruption and equipment damage. Over time, the artificial intelligence system will continuously learn and adapt to new data patterns, improving the accuracy and efficiency of its anomaly detection. This adaptive learning ability enables the system to continuously optimize as the production environment changes.

[0083] Through this comprehensive method of applying sensor technology and artificial intelligence, the monitoring of the washing machine valve production equipment becomes more intelligent and automated, which helps to detect potential problems in advance, reduce unexpected downtime, and improve the reliability and efficiency of the production process.

[0084] Figure 2 is a block diagram of an artificial intelligence-based washing machine valve production management system shown according to an exemplary embodiment. As Figure 2 shown, the system 200 includes:

[0085] The device vibration signal acquisition module 201 is configured to acquire a device vibration signal collected by a vibration sensor deployed on a washing machine valve production device;

[0086] The domain transformation module 202 is configured to perform domain transformation on the device vibration signal to obtain a device vibration time-frequency image;

[0087] The vibration correlation pattern analysis module 203 is configured to perform vibration correlation pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors;

[0088] The saliency enhancement fusion module 204 is configured to input the sequence of context device vibration local time-frequency semantic representation vectors into a saliency enhancement fusion module based on the sequence distribution cluster center to obtain a global device vibration time-frequency representation vector;

[0089] The management result determination module 205 is configured to determine a management result based on the global device vibration time-frequency representation vector.

[0090] Next, refer to Figure 3 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0091] As Figure 3 shown, the electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0092] Typically, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and a communication device 609. The communication device 609 can allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 3 an electronic device with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices can be implemented or had.

[0093] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above functions defined in the methods of the embodiments of the present disclosure are performed.

[0094] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: 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 the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0095] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed network.

[0096] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately and not be assembled into the electronic device.

[0097] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the 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., through the Internet using an Internet service provider).

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0099] The modules described in the embodiments of the present disclosure may be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation to the module itself in some cases. For example, the test parameter acquisition module may also be described as "the module for acquiring the device test parameters corresponding to the target device".

[0100] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, by way of non-limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0101] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0102] Figure 4 is an application scenario diagram of a production management method for washing machine valves based on artificial intelligence shown according to an exemplary embodiment. As Figure 4 shown, in this application scenario, first, device vibration signals collected by vibration sensors deployed on washing machine valve production equipment are obtained (for example, as Figure 4 illustrated by C shown); then, the obtained device vibration signals are input into a server deployed with a production management algorithm for washing machine valves based on artificial intelligence (for example, as Figure 4 illustrated by S shown), where the server can process the device vibration signals based on the production management algorithm for washing machine valves based on artificial intelligence to determine a management result.

[0103] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, technical solutions formed by mutually replacing the above features with (but not limited to) technical features having similar functions disclosed in the present disclosure.

[0104] Moreover, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the foregoing discussion, these should not be construed as limitations on the scope of the present disclosure. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, the various features that are described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0105] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. With regard to the apparatus in the foregoing embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be elaborated herein.

Claims

1. A washing machine valve production management method based on artificial intelligence, characterized in that: include: Obtaining equipment vibration signals collected by vibration sensors deployed on washing machine valve production equipment; Performing domain transformation on the device vibration signal to obtain a device vibration time-frequency image; Performing vibration association pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors; Inputting the sequence of the local time-frequency semantic representation vector of the context device vibration into a saliency enhancement fusion module based on the center of the sequence distribution cluster to obtain a global device vibration time-frequency representation vector; Determining a management result based on the global device vibration time-frequency representation vector; Wherein, determining the management result based on the global device vibration time-frequency representation vector includes: The global equipment vibration time-frequency representation vector is passed through a classifier-based management result generator to obtain the management result, and the management result is used to indicate whether the working state of the washing machine valve production equipment is abnormal; Wherein, the step of passing the global device vibration time-frequency representation vector through a classifier-based management result generator to obtain a management result comprises the following steps: Determine a first global device vibration time-frequency eigenvalue and a second global device vibration time-frequency eigenvalue at any two different positions of the global device vibration time-frequency representation vector; Determine the abnormal probability value corresponding to the abnormality of the working state of the washing machine valve production equipment and the normal probability value corresponding to the non-abnormality of the working state of the washing machine valve production equipment obtained by the global equipment vibration time-frequency representation vector through the classifier; Dividing the abnormal probability value by the normal probability value to obtain a global equipment vibration time-frequency relative class probability distribution value; Multiplying the abnormal probability value by the normal probability value to obtain a global equipment vibration time-frequency coordination class probability distribution value; Subtract the relative class probability distribution value of global device vibration time-frequency from the first global device vibration time-frequency characteristic value and the second global device vibration time-frequency characteristic value, and then multiply them to obtain a relative joint representation of global device vibration time-frequency; Adding the first global device vibration time-frequency characteristic value and the second global device vibration time-frequency characteristic value and then dividing by the global device vibration time-frequency coordination class probability distribution value to obtain a global device vibration time-frequency system response representation; Adding the global device vibration time-frequency relative joint representation to the global device vibration time-frequency system response representation to obtain a global device vibration time-frequency correction matrix as matrix values ​​at coordinates corresponding to different positions of the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue; Calculating the inner product of each row vector of the global device vibration time-frequency correction matrix and the global device vibration time-frequency representation vector to obtain an optimized global device vibration time-frequency representation vector; The optimized global equipment vibration time-frequency representation vector is passed through a classifier-based management result generator to obtain a management result.

2. The artificial intelligence-based washing machine valve production management method according to claim 1, characterized in that: Performing domain transformation on the device vibration signal to obtain a device vibration time-frequency image, including: The device vibration signal is subjected to wavelet transformation to obtain the device vibration time-frequency image.

3. The artificial intelligence-based washing machine valve production management method according to claim 2, characterized in that: Performing vibration association pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors, including: Performing image block processing on the device vibration time-frequency image to obtain a sequence of local time-frequency images of device vibration; The sequence of local time-frequency images of the device vibration is passed through a converter structure including an image block embedding layer to obtain a sequence of local time-frequency semantic representation vectors of the context device vibration.

4. The artificial intelligence-based washing machine valve production management method according to claim 3, characterized in that: Passing the sequence of the local time-frequency images of the device vibration through a converter structure including an image block embedding layer to obtain a sequence of the local time-frequency semantic representation vectors of the context device vibration, including: Passing the sequence of local time-frequency images of device vibration through the image block embedding layer to obtain a sequence of local time-frequency embedding feature vectors of device vibration; The sequence of the local time-frequency embedding feature vectors of the device vibration is passed through the converter structure to obtain the sequence of the local time-frequency semantic representation vectors of the context device vibration.

5. The artificial intelligence-based washing machine valve production management method according to claim 4, characterized in that: Inputting the sequence of the local time-frequency semantic representation vector of the context device vibration into a saliency enhancement fusion module based on the center of the sequence distribution cluster to obtain a global device vibration time-frequency representation vector, including: Calculating the mean vector of the sequence of the local time-frequency semantic representation vector of the context device vibration as the center of the sequence distribution cluster; Calculating the semantic association between each context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors and the center of the sequence distribution cluster to obtain a sequence of semantic associations; Normalizing the sequence of semantic associations to obtain a sequence of local significance association intensity factors of device vibration; The sequence of the local significance association strength factors of the device vibration is used as a weight sequence, and the vector-by-vector weighted sum of the sequence of the local time-frequency semantic representation vectors of the context device vibration is calculated to obtain the global device vibration time-frequency representation vector.

6. The artificial intelligence-based washing machine valve production management method according to claim 5, characterized in that: Calculating the semantic association between each context device vibration local time-frequency semantic representation vector in the sequence of context device vibration local time-frequency semantic representation vectors and the center of the sequence distribution cluster to obtain a sequence of semantic associations, including: Pass each of the context device vibration local time-frequency semantic representation vectors through a fully connected layer to obtain a sequence of context device vibration local time-frequency semantic fully connected encoding feature vectors; The transposed vector of the center of the sequence distribution cluster is calculated and multiplied by the vector of each of the local time-frequency semantic fully connected encoding feature vectors of the context device vibration to obtain the sequence of the semantic association degree.

7. The artificial intelligence-based washing machine valve production management method according to claim 6, characterized in that: The fully connected layer uses a sigmoid function.

8. The artificial intelligence-based washing machine valve production management method according to claim 7, characterized in that: The sequence of semantic associations is normalized to obtain a sequence of local significance association intensity factors of device vibration, including: The sequence of semantic associations is input into a softmax function for soft maximum normalization processing to obtain a sequence of local significance association intensity factors of the device vibration.

9. A washing machine valve production management system based on artificial intelligence, characterized in that: include: An equipment vibration signal acquisition module, used to acquire equipment vibration signals collected by vibration sensors deployed in washing machine valve production equipment; A domain transformation module, used for performing domain transformation on the device vibration signal to obtain a device vibration time-frequency image; A vibration association pattern analysis module, used for performing vibration association pattern analysis on the device vibration time-frequency image to obtain a sequence of context device vibration local time-frequency semantic representation vectors; A saliency enhancement fusion module, used for inputting the sequence of the local time-frequency semantic representation vector of the context device vibration into a saliency enhancement fusion module based on the center of the sequence distribution cluster to obtain a global device vibration time-frequency representation vector; A management result determination module, used to determine a management result based on the global device vibration time-frequency representation vector; Wherein, determining the management result based on the global device vibration time-frequency representation vector includes: The global equipment vibration time-frequency representation vector is passed through a classifier-based management result generator to obtain the management result, and the management result is used to indicate whether the working state of the washing machine valve production equipment is abnormal; Wherein, the step of passing the global device vibration time-frequency representation vector through a classifier-based management result generator to obtain a management result comprises the following steps: Determine a first global device vibration time-frequency eigenvalue and a second global device vibration time-frequency eigenvalue at any two different positions of the global device vibration time-frequency representation vector; Determine the abnormal probability value corresponding to the abnormality of the working state of the washing machine valve production equipment and the normal probability value corresponding to the non-abnormality of the working state of the washing machine valve production equipment obtained by the global equipment vibration time-frequency representation vector through the classifier; Dividing the abnormal probability value by the normal probability value to obtain a global equipment vibration time-frequency relative class probability distribution value; Multiplying the abnormal probability value by the normal probability value to obtain a global equipment vibration time-frequency coordination class probability distribution value; Subtract the relative class probability distribution value of global device vibration time-frequency from the first global device vibration time-frequency characteristic value and the second global device vibration time-frequency characteristic value, and then multiply them to obtain a relative joint representation of global device vibration time-frequency; Adding the first global device vibration time-frequency characteristic value and the second global device vibration time-frequency characteristic value and then dividing by the global device vibration time-frequency coordination class probability distribution value to obtain a global device vibration time-frequency system response representation; Adding the global device vibration time-frequency relative joint representation to the global device vibration time-frequency system response representation to obtain a global device vibration time-frequency correction matrix as matrix values ​​at coordinates corresponding to different positions of the first global device vibration time-frequency eigenvalue and the second global device vibration time-frequency eigenvalue; Calculating the inner product of each row vector of the global device vibration time-frequency correction matrix and the global device vibration time-frequency representation vector to obtain an optimized global device vibration time-frequency representation vector; The optimized global equipment vibration time-frequency representation vector is passed through a classifier-based management result generator to obtain a management result.

Images