Equipment state prediction method and system applied to smart factory

Abstract

The invention relates to the technical field of industrial prediction, and provides an equipment state prediction method and system applied to a smart factory. The method comprises the following steps: performing synchronous processing on working data of industrial equipment through a set nonlinear coupling item to generate a first data stream so as to construct a high-dimensional data space, and determining low-dimensional positioning information of points in the data space on a set dimension; generating a state feature code based on the working parameters of the industrial equipment, and determining the operating parameters of the industrial equipment through low-dimensional positioning information to generate an equipment topology model; and outputting the state parameters of the industrial equipment at the future moment through the topology mapping model. According to the method, the high-dimensional space is constructed, the low-dimensional features are extracted through diffusion mapping, the topology model is generated in combination with state coding and operation parameters, the future state of the equipment is accurately predicted, real-time monitoring and trend prediction of the state of the equipment are achieved, and the equipment management level and production efficiency of a smart factory are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of industrial forecasting technology, and more specifically, to a method and system for predicting equipment status applied to smart factories. Background Art

[0002] Driven by the Industrial Internet and intelligent manufacturing, smart factories have become a core focus of the transformation and upgrading of modern manufacturing. Leveraging advanced technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence, smart factories strive to achieve intelligent, automated, and efficient production processes. Equipment status prediction, a key technology in smart factories, plays a vital role in enabling predictive maintenance, reducing unplanned downtime, improving production efficiency, and reducing maintenance costs. By monitoring equipment operating status in real time and predicting potential failures, companies can optimize production plans and ensure the continuity and stability of the production process.

[0003] In the existing technology, device status is generally predicted through data analysis. However, in actual applications, device data is diverse, and it is often difficult to extract very clear and representative features from data of multiple types and dimensions, which leads to the problem of low accuracy of device status prediction results. Summary of the Invention

[0004] The present application provides a method and system for predicting equipment status in smart factories, which can at least to some extent solve the problem of low accuracy of equipment status prediction results.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of the present application, a method for predicting equipment status in a smart factory is provided, comprising: acquiring operating data of industrial equipment through intelligent sensors; synchronously processing the operating data through a set nonlinear coupling term to generate a first data stream; constructing a high-dimensional data space based on the first data stream, as well as a preset embedding dimension and time delay, and performing diffusion mapping in the data space to determine low-dimensional positioning information of points in the data space on a set dimension; generating a state feature code based on the operating parameters of the industrial equipment, determining the operating parameters of the industrial equipment through the low-dimensional positioning information, and generating an equipment topology model based on the state feature code and the operating parameters; and outputting the state parameters of the industrial equipment at a future moment through the topology mapping model.

[0007] In the present application, based on the aforementioned scheme, the working data is synchronously processed through the set nonlinear coupling item to generate a first data stream, including: normalizing the working data to generate second data; and iteratively calculating the second data through the set nonlinear coupling item to generate a first data stream in a synchronized state.

[0008] In the present application, based on the aforementioned scheme, a high-dimensional data space is constructed based on the first data stream, and a preset embedding dimension and time delay, and diffusion mapping is performed in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension, including: calculating the row parameters of the data space based on the first data stream, and the preset embedding dimension and time delay; determining the number of rows of the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters of the data space; performing diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension.

[0009] In the present application, based on the above-mentioned solution, the row parameter of the data space is calculated based on the first data stream, the preset embedding dimension and the time delay, including: based on the first data stream, the preset embedding dimension and the time delay, the row parameter M of the i-th row of the data space M is calculated as i , expressed as:

[0010] M i =[y i ,y i+τ ,y i+2τ ,…y i+(m-1)τ ]

[0011] Among them, y i represents the i-th data point in the first data stream Y, τ represents the preset time delay, and m represents the preset embedding dimension.

[0012] In the present application, based on the aforementioned scheme, the number of rows of the data space is determined based on a preset time series length, and a high-dimensional data space is constructed based on the number of rows and row parameters of the data space, including: based on the preset time series length, the embedding dimension and the time delay, determining the number of rows of the data space as N=T-(m-1)τ; based on the number of rows of the data space, stacking the row parameters in order to generate a high-dimensional data space.

[0013] In the present application, based on the aforementioned scheme, the state feature code is generated based on the working parameters of the industrial equipment, the operating parameters of the industrial equipment are determined through the low-dimensional positioning information, and the equipment topology model is generated based on the state feature code and the operating parameters, including: generating the state feature code of the industrial equipment based on the normalized amplitude and a preset number of bits when the industrial equipment is working; determining the operating parameters of the industrial equipment based on the low-dimensional positioning information, and converting the state feature code into a quantum feature code through the operating parameters; generating a state evolution path based on the quantum feature code and preset evolution parameters; analyzing the topological changes of the industrial equipment state based on the state evolution path to generate a device topology model.

[0014] In the present application, based on the aforementioned scheme, the state parameters of the industrial equipment at the future moment are output through the topological mapping model, including: generating the state parameters of the industrial equipment at the future moment through the topological mapping model; detecting whether there is an abnormality in the state parameters based on a preset state threshold; if there is an abnormality, generating an early warning file.

[0015] According to one aspect of the present application, a device status prediction system for a smart factory is provided, comprising:

[0016] An acquisition unit, used to acquire working data of industrial equipment through smart sensors;

[0017] a synchronization unit, configured to perform synchronization processing on the working data through a set nonlinear coupling term to generate a first data stream;

[0018] a mapping unit, configured to construct a high-dimensional data space based on the first data stream, a preset embedding dimension, and a time delay, and perform diffusion mapping in the data space to determine low-dimensional positioning information of points in the data space in a set dimension;

[0019] an encoding unit, configured to generate a state feature code based on the operating parameters of the industrial equipment, determine the operating parameters of the industrial equipment using the low-dimensional positioning information, and generate a device topology model based on the state feature code and the operating parameters;

[0020] The prediction unit is used to output the state parameters of the industrial equipment at a future moment through the topology mapping model.

[0021] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the device status prediction method applied to a smart factory as described in the above embodiment is implemented.

[0022] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the equipment status prediction method applied to a smart factory as described in the above embodiments.

[0023] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the device status prediction method for a smart factory provided in any of the aforementioned optional implementations.

[0024] The technical solution of this application obtains the working data of industrial equipment through intelligent sensors; synchronizes the working data through a set nonlinear coupling term to generate a first data stream; constructs a high-dimensional data space based on the first data stream, as well as a preset embedding dimension and time delay, and performs diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension; generates state feature codes based on the working parameters of the industrial equipment, determines the operating parameters of the industrial equipment through the low-dimensional positioning information, and generates a device topology model based on the state feature codes and the operating parameters; outputs the state parameters of the industrial equipment at a future moment through the topology mapping model. Equipment data is collected through intelligent sensors, and high-quality data streams are generated through nonlinear coupling synchronization processing. A high-dimensional space is constructed and diffusion mapping is performed to extract low-dimensional features. A topology model is generated by combining state codes and operating parameters, and finally the future state of the equipment is accurately predicted. This method realizes real-time monitoring and trend prediction of equipment status, can detect anomalies and issue warnings in a timely manner, and effectively improves the equipment management level and production efficiency of smart factories.

[0025] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0027] Figure 1The following schematically illustrates a flow chart of a method for predicting equipment status in a smart factory according to an embodiment of the present application.

[0028] Figure 2 The flowchart of determining low-dimensional positioning information in one embodiment of the present application is schematically shown.

[0029] Figure 3 A schematic diagram of an equipment status prediction system applied to a smart factory in one embodiment of the present application is shown schematically.

[0030] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0032] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0034] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0035] The implementation details of the technical solution of this application are described in detail below:

[0036] Figure 1The flowchart of the device status prediction method applied to a smart factory according to an embodiment of the present application is shown. Figure 1 As shown, the device status prediction method applied to a smart factory includes at least steps S110 to S150, which are described in detail as follows:

[0037] S110, obtains working data of industrial equipment through smart sensors.

[0038] In one embodiment of the present application, smart sensors are used to acquire operating data from industrial equipment. Various smart sensors, such as temperature sensors, pressure sensors, or vibration sensors, are deployed at key locations on the equipment. These sensors can sense changes in physical quantities during equipment operation in real time and convert these quantities into electrical signals. Subsequently, through operations such as analog-to-digital conversion, the analog signals are converted into digital operating data, which is ultimately transmitted to a data processing system to provide raw data for subsequent analysis and processing.

[0039] The raw data is then cleaned to remove noise, outliers, and duplicates to ensure accuracy and consistency. Missing data is also interpolated to complete the data series and provide a reliable data foundation for subsequent analysis.

[0040] Furthermore, data fusion and feature extraction can be performed. Using data fusion algorithms, data from multiple smart sensors is integrated and processed to obtain more comprehensive and accurate equipment status information. Feature extraction methods, such as time-domain and frequency-domain analysis, are then used to extract key features from the fused data that reflect the equipment's operating status. These features provide an important basis for subsequent equipment status monitoring and fault diagnosis, helping to promptly identify potential equipment issues and initiate appropriate maintenance measures.

[0041] S120 , performing synchronization processing on the working data through the set nonlinear coupling term to generate a first data stream.

[0042] In one embodiment of the present application, when the working data is synchronously processed by a preset nonlinear coupling item to generate a first data stream, the specific form and parameters of the nonlinear coupling item are first determined based on the equipment characteristics and data processing requirements. The nonlinear coupling item is used to describe the nonlinear correlation between different working data; then the working data is input into a synchronous processing model containing this nonlinear coupling item, so that the working data interacts and transforms in the model according to the set rules. In this process, working data from different sources and of different types influence and adjust each other under the action of the nonlinear coupling item, and finally the output forms a first data stream with synchronous characteristics and integrated multi-source data information, providing a more accurate and consistent equipment status information basis for subsequent analysis and processing.

[0043] In one embodiment of the present application, the working data is synchronously processed by setting a nonlinear coupling term to generate a first data stream, including:

[0044] performing normalization processing on the working data to generate second data;

[0045] The second data is iteratively operated through the set nonlinear coupling term to generate a first data stream in a synchronous state.

[0046] In one embodiment of the present application, the working data is normalized to generate second data X={x1(t), x2(t), ...x n (t)} to eliminate the dimension difference; where x n (t) represents the data slice generated at time t, n represents the total amount of working data, and t represents the generation time corresponding to the working data.

[0047] Afterwards, the second data is iteratively calculated through the set nonlinear coupling term to generate the first data stream Y in the synchronous state:

[0048]

[0049] Among them, f(x i ) represents the second data x i The dynamic characteristics of the second data x i 、x j The identifier of n represents the total amount of the second data, k ij represents the coupling strength matrix used for dynamic adjustment, sgn(·) represents the sign function, and α represents the fractional-order coupling coefficient.

[0050] The above calculation process introduces nonlinear coupling terms to force different sensor data streams to achieve generalized synchronization. Synchronous data processing effectively eliminates asynchrony between multi-source data. The generated first data stream can better reflect the actual operating status of the equipment and improve data quality.

[0051] Through synchronization, the above process enables data streams from different sensors to form similar trajectories and topological structures in phase space, facilitating subsequent feature extraction and fusion, ensuring that heterogeneous data forms topologically equivalent structures in phase space. The resulting first data stream exhibits greater correlation and consistency, helping to reduce errors and uncertainties in the data fusion process and improving data fusion accuracy. Furthermore, synchronization can suppress the effects of noise and interference on the data, improving the system's anti-interference capability, stability, and robustness.

[0052] S1 30, based on the first data stream, and the preset embedding dimension and time delay, construct a high-dimensional data space, and perform diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension.

[0053] In one embodiment of the present application, a high-dimensional data space is constructed based on the first data stream and diffusion mapping is performed to determine low-dimensional positioning information. First, each data point in the first data stream is regarded as a sample in the high-dimensional space, and the high-dimensional data space is constructed according to the data feature dimension; then, the similarity between samples in the high-dimensional data space is calculated to construct a similarity matrix; then, through the diffusion mapping algorithm, the similarity matrix is ​​subjected to operations such as feature decomposition to map the high-dimensional data to the low-dimensional space, thereby determining low-dimensional positioning information that can reflect the essential structure of the high-dimensional data, and providing basic data for subsequent analysis and processing.

[0054] like Figure 2 As shown, in one embodiment of the present application, based on the first data stream, and the preset embedding dimension and time delay, a high-dimensional data space is constructed, and diffusion mapping is performed in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension, including:

[0055] S2 1 0, calculating row parameters of the data space based on the first data stream, and a preset embedding dimension and time delay;

[0056] S220, determining the number of rows of the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters of the data space;

[0057] S230 , performing diffusion mapping in the data space to determine low-dimensional positioning information of points in the data space in a set dimension.

[0058] In one embodiment of the present application, during the construction of a high-dimensional data space, the input information includes: a synchronized first data stream, an embedding dimension, and a time delay. The first data stream is the result of the aforementioned processing steps and possesses synchronization characteristics; the embedding dimension and time delay are pre-set parameters used to control the accuracy and dimensionality of the high-dimensional data space reconstruction.

[0059] From the first data stream Y, a high-dimensional data space M is constructed according to the preset embedding dimension m and time delay τ. Specifically, the row parameter M of the i-th row of the data space M is expressed as:

[0060] M i =[y i ,y i+τ ,y i+2τ ,…y i+(m-1)τ ]

[0061] Among them, y i represents the i-th data point in the first data stream Y, τ represents the preset time delay, and m represents the preset embedding dimension, that is, the amount of data in the data space. The above formula is used to construct each row of the reconstructed high-dimensional data space M. It combines m data points in the original time series data Y separated by a time delay of τ to form a vector, which serves as a row in the data space.

[0062] After obtaining the row parameters, the number of rows in the data space is determined based on the preset time series length: N = T - (m - 1)τ, where T is the preset time series length. Based on the number of rows in the data space and the row parameters, the first data stream is stacked in order to generate a high-dimensional data space. The high-dimensional data space construction formula is used to combine the original time series data into rows in the data space.

[0063] In this process, as long as the embedding dimension m is large enough and the time delay τ is appropriately chosen, the data space of the original dynamical system can be reconstructed from the time series data. This high-dimensional data space reconstruction allows the data space of the dynamical system to be recovered from the chaotic time series data, providing richer information for subsequent analysis.

[0064] Perform diffusion mapping in the data space to determine the low-dimensional positioning information ψ of the i-th point in the data space M in the k-th dimension k (M i )for:

[0065]

[0066] Among them, k, j represent the identity of the feature vector, N represents the total number of feature vectors, M i 、M j They represent the row parameters of the i-th and j-th rows of the data space M, ε represents the kernel width parameter that controls the decay rate of similarity, and v k Represents the kth eigenvector of the Markov transition matrix. Low-dimensional positioning information can be understood as the location information of the first data in the simplified low-dimensional space, which is used to characterize the structure and relationship of the data. Here, calculations are performed for all k values ​​to obtain low-dimensional positioning information in different dimensions. This is done to calculate the low-dimensional positioning information of the i-th point in the reconstructed data space M in the k-th dimension. The coordinate value is obtained by taking a weighted sum of the similarities between all data points and the target point.

[0067] This process constructs a high-dimensional data space based on the first data stream, fully capturing the complex patterns and potential connections inherent in the data. By leveraging the local similarities between data points to construct a diffusion process, high-dimensional data is reduced to a low-dimensional space while preserving the data's essential characteristics and key topological structure. This reduces computational complexity while still accurately describing device status characteristics.

[0068] S140 , generating a state feature code based on the operating parameters of the industrial equipment, determining the operating parameters of the industrial equipment through the low-dimensional positioning information, and generating a device topology model based on the state feature code and the operating parameters.

[0069] In one embodiment of the present application, when generating state feature codes based on the working parameters of industrial equipment, determining operating parameters through low-dimensional positioning information, and generating an equipment topology model based on the state feature codes and operating parameters, the working parameters of the industrial equipment are first analyzed and processed, and key information is extracted to generate state feature codes; then, based on the positional relationship of the equipment state in the low-dimensional space reflected by the low-dimensional positioning information, the corresponding operating parameters are determined in combination with the equipment operating laws and physical characteristics; finally, the equipment state information represented by the state feature codes is fused with the operating parameters, and according to the connection relationship and interaction between the various parts of the equipment, a topological model that can describe the overall structure and operating state characteristics of the equipment is constructed, providing an important basis for equipment performance evaluation, fault prediction, etc.

[0070] In one embodiment of the present application, a state feature code is generated based on the operating parameters of the industrial equipment, the operating parameters of the industrial equipment are determined using the low-dimensional positioning information, and a device topology model is generated based on the state feature code and the operating parameters, including:

[0071] generating a state feature code of the industrial equipment based on a normalized amplitude of the industrial equipment when it is working and a preset number of bits;

[0072] determining operating parameters of the industrial equipment based on the low-dimensional positioning information, and converting the state feature code into a quantum feature code using the operating parameters;

[0073] Generate a state evolution path based on the quantum characteristic code and preset evolution parameters;

[0074] The topological changes of the industrial equipment state are analyzed based on the state evolution path to generate an equipment topology model.

[0075] In one embodiment of the present application, based on the normalized amplitude of the industrial equipment during operation and a preset system scale parameter q, a state feature code |φ0> of the industrial equipment is generated as follows:

[0076]

[0077] Among them, |φ0> represents the state feature code of the industrial equipment obtained after encoding, n represents the state index of the industrial equipment, λ n represents the normalized amplitude of the industrial equipment when it is working, |n> represents the basic state parameters of the industrial equipment when it is working stably, and q represents the system scale parameter of the industrial equipment system, which determines the scale of the industrial equipment system to be simulated, that is, how many quantum bits are used to represent and process this information.

[0078] In one embodiment of the present application, the operating parameters of the industrial equipment are determined based on the low-dimensional positioning information as follows:

[0079]

[0080] in,

[0081] Among them, J uv Represents the preset coupling coefficient, which is used to measure the interaction strength between quantum bits u and v;

[0082] h u represents the transverse magnetic field parameter, which is used to measure the flipping strength of the quantum bit u in the X direction;

[0083] γ u Represents the preset positioning weight coefficient, which is used to adjust the low-dimensional positioning information ψ k The degree of impact on quantum bit u;

[0084] ψ k Represents low-dimensional positioning information, and u and v represent the identifiers of quantum bits.

[0085] The calculated operating parameters in this embodiment are used to characterize the operating rules of the equipment system.

[0086] Subsequently, the operating parameters of the industrial equipment are adjusted through quantum annealing, and the classical state characteristic code is converted into the quantum characteristic code |φ(t)> at time t:

[0087]

[0088] Among them, H t represents the operating parameters at time t, r represents the identifier of the quantum bit, and |φ0> represents the state feature encoding.

[0089] The quantum annealing algorithm simulates the evolution of a quantum system according to the rules of its operating parameters. Based on classical, deterministic characteristic information, it guides the quantum system to gradually find its lowest energy state and gradually transform into a superposition state unique to the quantum world. The annealing algorithm continuously adjusts the state of the quantum system, guiding it towards a lower energy, more stable state. In this process, the original classical, single characteristic information is gradually encoded and stored in the superposition characteristics of the quantum state, ultimately forming the desired quantum superposition state, that is, the quantum characteristic encoding, completing the conversion of classical to quantum information. This not only increases the dimensionality of characteristic expression but also leverages quantum parallelism, achieving higher efficiency and accuracy.

[0090] In one embodiment of the present application, a state evolution path is generated based on the quantum feature code and preset evolution parameters. When constructing the state evolution path, the quantum feature code and evolution parameters are first input. The quantum feature code and evolution parameters are then combined through nonlinear processing. A state evolution path is constructed according to preset logic and operation rules.

[0091] Through this state evolution path, we can simulate the evolution process and dynamic behavior of industrial equipment under different conditions, obtain the state information of the system at different time points, further analyze the topological changes of the industrial equipment state, and generate a device topology model. In this embodiment, the topological changes focus on changes in the overall structure and connection mode of the equipment state, rather than subtle local changes. By analyzing these topological changes, we can reveal the patterns and laws of the equipment's transitions between different states, and then intuitively display the interaction relationship and energy flow between the various components of the equipment, providing a more comprehensive perspective for state prediction.

[0092] S150: Outputting the state parameters of the industrial equipment at a future time through the topology mapping model.

[0093] In one embodiment of the present application, when predicting the state parameters of industrial equipment at a future moment through a topological mapping model, the historical state data and related feature information of the industrial equipment obtained in the early stage are first input into the trained topological mapping model. The model performs nonlinear transformation and mapping processing on the input data based on the equipment topology structure and mapping relationship constructed internally, and mines the potential correlation and change rules between the data; then, based on the pattern learned by the model and combined with the current equipment status information, it infers the state that the equipment may be in at a specific moment in the future, and then obtains the corresponding state parameters, such as the predicted values ​​of key parameters such as temperature, pressure and speed, which provide an important reference for equipment maintenance and management.

[0094] In one embodiment of the present application, outputting the state parameters of the industrial equipment at a future time through the topology mapping model includes:

[0095] Generating state parameters of the industrial equipment at a future time through the topology mapping model;

[0096] Based on a preset state threshold, detecting whether the state parameter is abnormal;

[0097] If there is an abnormality, an early warning file will be generated.

[0098] The topology mapping model outputs the state parameters of the industrial equipment at a future time. The predicted state parameters are compared with a preset state threshold, which is set based on the normal operating range of the equipment. If the predicted parameters exceed this threshold, it can be determined that the state parameters are abnormal, indicating that the equipment may malfunction or performance degradation at a future time.

[0099] Once a status parameter anomaly is detected, relevant information is automatically collected, such as the specific value of the anomaly parameter and the time of occurrence. Based on this information, an early warning document is generated, containing the possible fault type, severity, and recommended countermeasures for subsequent processing and analysis. The topology mapping model outputs the device's status parameters at future times, enabling accurate prediction of device operating trends. This method promptly detects device status anomalies and generates early warnings, effectively avoiding equipment downtime and improving production efficiency and equipment management in smart factories.

[0100] The technical solution of this application obtains the working data of industrial equipment through intelligent sensors; synchronizes the working data through a set nonlinear coupling term to generate a first data stream; constructs a high-dimensional data space based on the first data stream, as well as a preset embedding dimension and time delay, and performs diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension; generates state feature codes based on the working parameters of the industrial equipment, determines the operating parameters of the industrial equipment through the low-dimensional positioning information, and generates a device topology model based on the state feature codes and the operating parameters; outputs the state parameters of the industrial equipment at a future moment through the topology mapping model. Equipment data is collected through intelligent sensors, and high-quality data streams are generated through nonlinear coupling synchronization processing. A high-dimensional space is constructed and diffusion mapping is performed to extract low-dimensional features. A topology model is generated by combining state codes and operating parameters, and finally the future state of the equipment is accurately predicted. This method realizes real-time monitoring and trend prediction of equipment status, can detect anomalies and issue warnings in a timely manner, and effectively improves the equipment management level and production efficiency of smart factories.

[0101] The following describes an embodiment of the device state prediction system applied to a smart factory of the present application, which can be used to execute the device state prediction method applied to a smart factory in the above-mentioned embodiment of the present application. It can be understood that the device state prediction system applied to a smart factory can be a computer program (including program code) running on a computer device. For example, the device state prediction system applied to a smart factory is an application software; the device state prediction system applied to a smart factory can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device state prediction system applied to a smart factory of the present application, please refer to the embodiment of the device state prediction method applied to a smart factory of the present application.

[0102] Figure 3 A block diagram of an equipment status prediction system applied to a smart factory according to an embodiment of the present application is shown.

[0103] Reference Figure 3 As shown, according to one embodiment of the present application, a device status prediction system applied to a smart factory includes:

[0104] An acquisition unit 310 is configured to acquire operating data of industrial equipment through smart sensors;

[0105] a synchronization unit 320, configured to perform synchronization processing on the working data through a set nonlinear coupling term to generate a first data stream;

[0106] A mapping unit 330 is configured to construct a high-dimensional data space based on the first data stream, a preset embedding dimension, and a time delay, and perform diffusion mapping in the data space to determine low-dimensional positioning information of points in the data space in a set dimension.

[0107] an encoding unit 340 configured to generate a state feature code based on the operating parameters of the industrial equipment, determine the operating parameters of the industrial equipment using the low-dimensional positioning information, and generate a device topology model based on the state feature code and the operating parameters;

[0108] The prediction unit 350 is configured to output the state parameters of the industrial equipment at a future moment through the topology mapping model.

[0109] In the present application, based on the aforementioned scheme, the working data is synchronously processed through the set nonlinear coupling item to generate a first data stream, including: normalizing the working data to generate second data; and iteratively calculating the second data through the set nonlinear coupling item to generate a first data stream in a synchronized state.

[0110] In the present application, based on the aforementioned scheme, a high-dimensional data space is constructed based on the first data stream, and a preset embedding dimension and time delay, and diffusion mapping is performed in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension, including: calculating the row parameters of the data space based on the first data stream, and the preset embedding dimension and time delay; determining the number of rows of the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters of the data space; performing diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension.

[0111] In the present application, based on the above-mentioned solution, the row parameter of the data space is calculated based on the first data stream, the preset embedding dimension and the time delay, including: based on the first data stream, the preset embedding dimension and the time delay, the row parameter M of the i-th row of the data space M is calculated as i , expressed as:

[0112] M i =[y i ,y i+τ ,y i+2τ ,…y i+(m-1)τ ]

[0113] Among them, y i represents the i-th data point in the first data stream Y, τ represents the preset time delay, and m represents the preset embedding dimension.

[0114] In the present application, based on the aforementioned scheme, the number of rows of the data space is determined based on a preset time series length, and a high-dimensional data space is constructed based on the number of rows and row parameters of the data space, including: based on the preset time series length, the embedding dimension and the time delay, determining the number of rows of the data space as N=T-(m-1)τ; based on the number of rows of the data space, stacking the row parameters in order to generate a high-dimensional data space.

[0115] In the present application, based on the aforementioned scheme, the state feature code is generated based on the working parameters of the industrial equipment, the operating parameters of the industrial equipment are determined through the low-dimensional positioning information, and the equipment topology model is generated based on the state feature code and the operating parameters, including: generating the state feature code of the industrial equipment based on the normalized amplitude and a preset number of bits when the industrial equipment is working; determining the operating parameters of the industrial equipment based on the low-dimensional positioning information, and converting the state feature code into a quantum feature code through the operating parameters; generating a state evolution path based on the quantum feature code and preset evolution parameters; analyzing the topological changes of the industrial equipment state based on the state evolution path to generate a device topology model.

[0116] In the present application, based on the aforementioned scheme, the state parameters of the industrial equipment at the future moment are output through the topological mapping model, including: generating the state parameters of the industrial equipment at the future moment through the topological mapping model; detecting whether there is an abnormality in the state parameters based on a preset state threshold; if there is an abnormality, generating an early warning file.

[0117] The technical solution of this application obtains the working data of industrial equipment through intelligent sensors; synchronizes the working data through a set nonlinear coupling term to generate a first data stream; constructs a high-dimensional data space based on the first data stream, as well as a preset embedding dimension and time delay, and performs diffusion mapping in the data space to determine the low-dimensional positioning information of the points in the data space on the set dimension; generates state feature codes based on the working parameters of the industrial equipment, determines the operating parameters of the industrial equipment through the low-dimensional positioning information, and generates a device topology model based on the state feature codes and the operating parameters; outputs the state parameters of the industrial equipment at a future moment through the topology mapping model. Equipment data is collected through intelligent sensors, and high-quality data streams are generated through nonlinear coupling synchronization processing. A high-dimensional space is constructed and diffusion mapping is performed to extract low-dimensional features. A topology model is generated by combining state codes and operating parameters, and finally the future state of the equipment is accurately predicted. This method realizes real-time monitoring and trend prediction of equipment status, can detect anomalies and issue warnings in a timely manner, and effectively improves the equipment management level and production efficiency of smart factories.

[0118] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0119] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] In this embodiment, the computer system includes a central processing unit (CPU) 401, which can execute various appropriate actions and processes based on programs stored in read-only memory (ROM) 402 or programs loaded from storage unit 408 into random access memory (RAM) 403, such as executing the device status prediction method for a smart factory described in the above embodiment. RAM 403 also stores various programs and data required for system operation. CPU 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output interface 405 is also connected to bus 404.

[0121] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read therefrom can be installed into the storage section 408 as needed.

[0122] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the system of the present application are performed.

[0123] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. 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 of computer-readable storage media 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), a 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 application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0126] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0127] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device implements the device status prediction method for a smart factory described in the above embodiments.

[0128] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0129] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0130] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0131] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A device status prediction method applied to a smart factory, characterized in that: include: Obtain working data of industrial equipment through smart sensors; Synchronously processing the working data through a set nonlinear coupling term to generate a first data stream; Based on the first data stream, and a preset embedding dimension and time delay, a high-dimensional data space is constructed, and diffusion mapping is performed in the data space to determine low-dimensional positioning information of points in the data space on the set dimension; generating a state feature code based on the operating parameters of the industrial equipment, determining the operating parameters of the industrial equipment through the low-dimensional positioning information, and generating a device topology model based on the state feature code and the operating parameters; The state parameters of the industrial equipment at a future moment are outputted through the topology mapping model.

2. The device status prediction method applied to a smart factory according to claim 1 is characterized in that: The working data is synchronously processed by using a set nonlinear coupling term to generate a first data stream, including: performing normalization processing on the working data to generate second data; An iterative operation is performed on the second data through the set nonlinear coupling term to generate a first data stream in a synchronous state.

3. The device status prediction method applied to a smart factory according to claim 1 is characterized in that: Based on the first data stream, and the preset embedding dimension and time delay, a high-dimensional data space is constructed, and diffusion mapping is performed in the data space to determine low-dimensional positioning information of points in the data space on the set dimension, including: Calculating row parameters of the data space based on the first data stream, and a preset embedding dimension and time delay; Determining the number of rows of the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters of the data space; Diffusion mapping is performed in the data space to determine low-dimensional positioning information of points in the data space in a set dimension.

4. The device status prediction method applied to a smart factory according to claim 3 is characterized in that: Calculating row parameters of the data space based on the first data stream, and the preset embedding dimension and time delay includes: Based on the first data stream, and the preset embedding dimension and time delay, the row parameter M of the i-th row of the data space M is i , expressed as: M i =[and i ,and i+τ ,and i+2τ ,…and i+(m-1)τ ] Among them, y i represents the i-th data point in the first data stream Y, τ represents a preset time delay, m represents a preset embedding dimension, and the row parameter represents the number of elements in each row in the data space.

5. The device status prediction method applied to a smart factory according to claim 4 is characterized in that: Determining the number of rows in the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters in the data space, including: Based on the preset time series length, the embedding dimension, and the time delay, determining the number of rows in the data space to be N=T-(m-1)τ; Based on the number of rows of the data space and the row parameters, the first data streams are stacked in order to generate a high-dimensional data space.

6. The device status prediction method for smart factories according to claim 1 is characterized in that: Generating a state feature code based on the operating parameters of the industrial equipment, determining the operating parameters of the industrial equipment through the low-dimensional positioning information, and generating a device topology model based on the state feature code and the operating parameters, including: generating a state feature code of the industrial equipment based on a normalized amplitude of the industrial equipment when it is working and a preset number of bits; determining operating parameters of the industrial equipment based on the low-dimensional positioning information, and converting the state feature code into a quantum feature code using the operating parameters; Generate a state evolution path based on the quantum characteristic code and preset evolution parameters; The topological changes of the industrial equipment state are analyzed based on the state evolution path to generate an equipment topology model.

7. The device status prediction method for smart factories according to claim 1 is characterized in that: Outputting the state parameters of the industrial equipment at a future time through the topology mapping model includes: Generating state parameters of the industrial equipment at a future time through the topology mapping model; Based on a preset state threshold, detecting whether the state parameter is abnormal; If there is an abnormality, an early warning file will be generated.

8. An equipment status prediction system applied to a smart factory, characterized in that: include: An acquisition unit, used to acquire working data of industrial equipment through smart sensors; a synchronization unit, configured to perform synchronization processing on the working data through a set nonlinear coupling term to generate a first data stream; a mapping unit, configured to construct a high-dimensional data space based on the first data stream, a preset embedding dimension, and a time delay, and perform diffusion mapping in the data space to determine low-dimensional positioning information of points in the data space in a set dimension; an encoding unit, configured to generate a state feature code based on the operating parameters of the industrial equipment, determine the operating parameters of the industrial equipment using the low-dimensional positioning information, and generate a device topology model based on the state feature code and the operating parameters; The prediction unit is used to output the state parameters of the industrial equipment at a future moment through the topology mapping model.

9. The equipment status prediction system for smart factories according to claim 7 is characterized in that: The working data is synchronously processed by using a set nonlinear coupling term to generate a first data stream, including: performing normalization processing on the working data to generate second data; An iterative operation is performed on the second data through the set nonlinear coupling term to generate a first data stream in a synchronous state.

10. The equipment status prediction system for smart factories according to claim 7, characterized in that: Based on the first data stream, and the preset embedding dimension and time delay, a high-dimensional data space is constructed, and diffusion mapping is performed in the data space to determine low-dimensional positioning information of points in the data space on the set dimension, including: Calculating row parameters of the data space based on the first data stream, and a preset embedding dimension and time delay; Determining the number of rows of the data space based on a preset time series length, and constructing a high-dimensional data space based on the number of rows and row parameters of the data space; Diffusion mapping is performed in the data space to determine low-dimensional positioning information of points in the data space in a set dimension.

Images