Equipment operation trend prediction method and system based on big data, equipment and medium

Abstract

The invention discloses a big data equipment operation trend prediction method and system, equipment and a medium. The method comprises the following steps: acquiring equipment operation data collected in real time; performing cleaning, dimension reduction and feature extraction on the acquired data to obtain preprocessed data; performing equipment future operation trend prediction on the preprocessed data by using a long short-term memory network model to obtain a trend prediction result; the operation state of the equipment is judged in real time through a fault diagnosis model, and when abnormity is detected, an early warning signal is sent out; generating an equipment health score according to a trend prediction result; and visually displaying the real-time state, the trend prediction result and the health score of the equipment. According to the method, the fault prediction accuracy is improved, and the equipment downtime is reduced. And the fault diagnosis model is adopted to identify the abnormal state of the equipment in real time, and early warning is given out for the abnormal state, so that automation of fault early warning is realized. The utilization efficiency of the equipment operation data is improved, and high efficiency and intelligence of equipment management are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management, and in particular to a method, system, equipment and medium for predicting equipment operation trends based on big data. Background Art

[0002] With the development of the Internet of Things (IoT) and Industry 4.0, more and more equipment is equipped with sensors that can collect operating status and environmental parameters in real time. This equipment management model has greatly improved production efficiency and maintenance level, but it also brings challenges in data management, real-time and fault prediction. Especially in the management of large-scale industrial equipment, equipment failure can lead to serious economic losses and safety risks, so it is particularly important to establish an efficient equipment operation trend prediction system.

[0003] In recent years, trend prediction and fault warning technologies based on big data and artificial intelligence (AI) have developed rapidly. Machine learning and deep learning algorithms have shown great potential in predictive maintenance of equipment, especially by learning from historical and real-time data of equipment operation, which can detect potential faults at an early stage and avoid equipment downtime and maintenance costs. However, due to the huge amount of data and the variety of equipment types, traditional single algorithms often cannot meet the needs of complex application environments.

[0004] The existing equipment fault detection systems include rule-based fault detection systems, prediction systems based on traditional statistical methods, predictive maintenance systems based on machine learning, and prediction systems based on deep learning.

[0005] Traditional fault detection systems often use methods based on thresholds or empirical rules. These rules use preset alarm thresholds to determine whether the equipment is in an abnormal state. However, the disadvantage of this solution is that the threshold is difficult to adjust automatically, and the rule setting mainly relies on the historical data of the equipment, lacking the ability to predict future trends. When the operating status of the equipment changes, the system cannot dynamically update the rules, which is prone to false positives or false negatives.

[0006] Statistical methods, such as time series analysis and regression analysis, are widely used in the field of equipment health monitoring, mainly to detect anomalies in equipment operation data and predict short-term trends of equipment. However, statistical methods are easily affected by noise in multivariate situations and lack the ability to handle complex nonlinear relationships. Therefore, they cannot achieve ideal prediction results for data with large nonlinear changes.

[0007] Algorithms such as random forests, support vector machines (SVMs), and decision trees are widely used for equipment condition monitoring and fault prediction. Predictive maintenance systems based on machine learning are gradually emerging. These systems are usually able to model based on historical data, which improves the accuracy of predictions to a certain extent, but they often perform poorly in processing time series data. In addition, the high computational cost of machine learning methods also limits their real-time performance, making it difficult for some algorithms to achieve edge computing and real-time fault warnings.

[0008] Deep learning models, such as long short-term memory (LSTM) and convolutional neural networks (CNN), have strong performance in processing complex time series data. LSTM can effectively capture the long-term dependencies of data and is suitable for equipment operation trend prediction and fault diagnosis. However, relying solely on deep learning models for prediction has high computational costs and the risk of overfitting, making it difficult to adapt to the personalized needs of diverse equipment. At the same time, existing LSTM and CNN models do not fully utilize edge computing resources and lack optimization for data transmission. Summary of the invention

[0009] The purpose of the present invention is to provide a method, system, device and medium for predicting equipment operation trends based on big data to solve the technical problems existing in the prior art.

[0010] The present invention is achieved through the following technical solutions:

[0011] In a first aspect, an embodiment of the present invention provides a method for predicting equipment operation trends based on big data, comprising the following steps:

[0012] Obtain real-time collected equipment operation data;

[0013] Clean, reduce dimension and extract features of the acquired data to obtain preprocessed data;

[0014] The long short-term memory network model is used to predict the future operation trend of the equipment based on the preprocessed data to obtain the trend prediction results;

[0015] Use fault diagnosis models to determine the operating status of equipment in real time, and issue warning signals when abnormalities are detected;

[0016] Generate equipment health scores based on trend prediction results;

[0017] Visualize the real-time status, trend prediction results and health score of the equipment.

[0018] Furthermore, the specific methods for cleaning and reducing the dimension of the acquired data include:

[0019] Discrete wavelet transform method is used to identify and filter noise;

[0020] Principal component analysis was used to reduce the data dimension.

[0021] Furthermore, the specific method of using the fault diagnosis model to judge the operating status of the equipment in real time includes:

[0022] Set the objective function:

[0023]

[0024] where ω is the weight vector, ||w|| 2 is the square of the second norm of the weight vector, λ is a positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the data set;

[0025] The decision function is used to determine whether the equipment is operating normally. The decision function is:

[0026] f(x)=sign(w·x+b);

[0027] Where x is the input vector. When f(x)>0, the device operates normally. When f(x)≤0, a fault warning is triggered.

[0028] Furthermore, the specific method of generating a device health score based on the trend prediction result includes:

[0029] Find the maximum and minimum values ​​based on the historical trend data sequence of the device, and calculate the average value of the historical data;

[0030] Normalize historical trend data to the interval of [0, 1];

[0031] Calculate the difference value of the current device status value after normalization;

[0032] The device health score is calculated based on the health score formula and the difference value.

[0033] In a second aspect, an embodiment of the present invention provides a device operation trend prediction system based on big data, comprising: a data acquisition module, a data preprocessing module, a trend prediction module, a fault warning module, a health scoring module and a user interaction module.

[0034] The data acquisition module is used to acquire the equipment operation data collected in real time and transmit it to the data preprocessing module for processing;

[0035] The data preprocessing module is used to clean, reduce the dimension and extract features of the collected data to obtain preprocessed data;

[0036] The trend prediction module uses a long short-term memory network model to predict the future operation trend of the equipment on the preprocessed data to obtain a trend prediction result;

[0037] The fault warning module uses a fault diagnosis model to determine the operating status of the equipment in real time, and sends out a warning signal when an abnormality is detected;

[0038] The health scoring module is used to perform health scoring after normalizing the historical trend of the device to obtain a health score;

[0039] The user interaction module is used to visually display the real-time status, trend prediction results and health score of the device.

[0040] Furthermore, the data preprocessing module includes a data cleaning unit and a data dimension reduction unit. The data cleaning unit uses a discrete wavelet transform method to identify and filter noise, and the data dimension reduction unit uses a principal component analysis method to reduce data dimensions.

[0041] Furthermore, the fault warning module uses a fault diagnosis model to determine the operating status of the equipment in real time, including:

[0042] Set the objective function:

[0043]

[0044] where ω is the weight vector, ||w|| 2 is the square of the second norm of the weight vector, λ is a positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the data set;

[0045] The decision function is used to determine whether the equipment is operating normally. The decision function is:

[0046] f(x)=sign(w·x+b);

[0047] Where x is the input vector. When f(x)>0, the device operates normally. When f(x)≤0, a fault warning is triggered.

[0048] Furthermore, the health scoring module includes a normalization processing unit and a scoring unit. The normalization processing unit finds the maximum and minimum values ​​according to the historical trend data sequence of the device, calculates the average value of the historical data, normalizes the historical trend data to the interval of [0, 1], and calculates the difference value of the current device status value after normalization; the scoring unit is used to calculate the device health score according to the health scoring formula and the difference value.

[0049] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor, an input device, an output device and a memory, wherein the processor is connected to the input device, the output device and the memory, respectively, the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method described in the above embodiment.

[0050] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the above embodiment.

[0051] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0052] The embodiment of the present invention provides a method, system, device and medium for predicting the equipment operation trend based on big data, which uses the LSTM model to predict the trend of the future state of the equipment, improves the accuracy of fault prediction, and reduces the equipment downtime. The fault diagnosis model is used to identify the abnormal state of the equipment in real time, and an early warning is issued for the abnormal state, realizing the automation of fault early warning. At the same time, it also improves the utilization efficiency of equipment operation data, and realizes efficient and intelligent equipment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0054] Figure 1 A flowchart of a method for predicting equipment operation trends based on big data provided by the first embodiment of the present invention;

[0055] Figure 2 A structural block diagram of a device operation trend prediction system based on big data provided by another embodiment of the present invention;

[0056] Figure 3 A structural block diagram of an electronic device provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0058] Example 1

[0059] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting equipment operation trends based on big data, comprising the following steps:

[0060] Obtain real-time collected equipment operation data;

[0061] Clean, reduce dimension and extract features of the acquired data to obtain preprocessed data;

[0062] The long short-term memory network model is used to predict the future operation trend of the equipment based on the preprocessed data to obtain the trend prediction results;

[0063] Use fault diagnosis models to determine the operating status of equipment in real time, and issue warning signals when abnormalities are detected;

[0064] Generate equipment health scores based on trend prediction results;

[0065] Visualize the real-time status, trend prediction results and health score of the equipment.

[0066] In this embodiment, the data acquisition module acquires the device operation data collected in real time from the device sensor, and the operation data includes: temperature, pressure, vibration, etc. The acquired data can be subsequently analyzed and processed through the cloud or edge node. When the data acquisition module acquires data, the sensor acquisition frequency and data range can be configured, and the data can be transmitted in real time through the Internet of Things communication protocol such as MQTT. The data is recorded by timestamp to ensure the continuity and traceability of the data. The acquired data is cleaned, reduced in dimension, and features are extracted to ensure the accuracy and validity of the data.

[0067] The discrete wavelet transform (DWT) method is used for data cleaning to identify and filter noise. The discrete wavelet transform formula is:

[0068]

[0069] Among them, X(t) is a function of time t, representing the original signal or data, c k is a coefficient, usually called a wavelet coefficient, which represents the weight of the original signal at different scales and positions. j，k(t) is a wavelet function, where j and k are parameters, representing scale and location respectively.

[0070] The principal component analysis (PCA) method is used to reduce data dimension. By reducing the data dimension, data redundancy is reduced. The formula is:

[0071] Z=W·X,

[0072] Among them, X is the original data matrix, W is the feature vector matrix, and Z is the data matrix after dimensionality reduction.

[0073] The long short-term memory network (LSTM) model is used to predict the future operation trend of the equipment based on the preprocessed data. LSTM (Long Short-Term Memory) is a special recurrent neural network (RNN) in deep learning, which is particularly suitable for processing time series data. By introducing memory units and gating mechanisms, it effectively solves the gradient vanishing and gradient exploding problems faced by ordinary RNN in long sequences.

[0074] LSTM basic structure: Input gate, forget gate and output gate are the core components of LSTM. They control the flow of information in the network and determine which information is remembered and which is forgotten. Memory cells store information states that change over time.

[0075] Long Short-Term Memory Network: A deep learning algorithm suitable for time series data that can capture long-term and short-term dependencies in equipment operation data.

[0076] LSTM calculation process:

[0077] Forget Gate: Determines which information is discarded. The Forget Gate combines the state of the previous time step with the current input through a Sigmoid function, and the output value is between 0 and 1, indicating the proportion of information retained.

[0078] f t =σ(W f ·[h t-1 , x t ]+b f ),

[0079] Among them, W f is the forget gate weight matrix, b f is the bias parameter, h t-1 is the hidden state of the previous time step, x t is the current input, f t is the output of the forget gate.

[0080] Input Gate: Determines which new information needs to be added to the memory cell. First, a Sigmoid layer is used to determine which values ​​need to be updated, and then a Tanh layer is used to generate new candidate memory cell contents. The formula for the input gate is:

[0081] i t =σ(W i ·[ht-1 , x t ]+b i )

[0082]

[0083] Among them, i t is the output of the input gate, σ is the sigmoid activation function, W i is the weight matrix of the input gate, b i is the bias vector of the input gate, is the candidate cell state at time step t, W C is the weight matrix of the candidate cell state, b C is the bias vector of the candidate cell state.

[0084] Update the state of the memory cell: Update the state of the memory cell by combining the results of the forget gate and the input gate.

[0085]

[0086] Among them, C t is the cell state at the current moment, C t-1 is the cell state at the previous moment.

[0087] The formula of output gate is:

[0088] o t =σ(W o ·[h t-1 , x t ]+b o )

[0089] h t =o t tanh(C t ),

[0090] Among them, t is the output value of the output gate at time step t, W o is the weight matrix of the output gate, b o is the bias vector of the output gate, h t is the hidden state at time step t.

[0091] Through this mechanism, LSTM dynamically adjusts the contents of memory cells in each time step so that important information can be retained, improving the ability to model long-term dependent information.

[0092] Among them, the fault diagnosis model uses support vector machine (SVM) for fault identification. Support vector machine (SVM) is a binary classification model. Its basic model is a linear classifier with the largest interval defined in the feature space. The largest interval makes it different from the perceptron. SVM also includes kernel techniques, which makes it a nonlinear classifier in essence. The specific methods of using the fault diagnosis model to judge the operating status of the equipment in real time include:

[0093] Set the objective function:

[0094]

[0095] Here λ is a constant used to weigh the regularization term and loss items The importance of. Among them, ω is the weight vector, ||w|| 2 is the square of the bi-norm of the weight vector, λ is the positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the dataset.

[0096] The decision function is used to determine whether the equipment is operating normally. The decision function is:

[0097] f(x)=sign(w·x+b);

[0098] Among them, x is the input vector, w is the weight vector, b is the bias term, when f(x)>0, the equipment operates normally, and when f(x)≤0, a fault warning is triggered. The specific method of generating a device health score based on the trend prediction result includes the following steps: find the maximum and minimum values ​​based on the historical trend data sequence of the device, and calculate the average value of the historical data.

[0099] Normalize historical trend data to the interval of [0, 1];

[0100] Calculate the difference value of the current device status value after normalization;

[0101] The device health score is calculated based on the health score formula and the difference value.

[0102] The health score is a score generated based on the LSTM prediction results, which is calculated by normalizing the historical trends of the device status. The device health score provides a relative score to reflect the health status of the device by comparing the current status of the device with the historical operating trends. Normalization ensures that different data sources are compared on the same scale, making it easier to apply the trends of historical data to current data.

[0103] Assume that the device health score is S, which indicates the health of the device. Specifically, the score is usually in the range of 0 to 100, with 100 representing the best state and 0 representing the worst state.

[0104] S = 100-α×D,

[0105] Where D is the difference between the current equipment status and the health standard value (Deviation), and α is the smoothing coefficient, which is used to adjust the sensitivity of the score.

[0106] The normalization process is to normalize the historical trend of the device to the [0,1] interval to facilitate effective use of the scoring system.

[0107] Assume that the operating data sequence of the equipment in the past N days is X = {x1, x2, ... x N}, then its maximum and minimum values ​​are X max =max(X),X min =min(X), the formula for normalizing the data to the interval [0,1] is:

[0108]

[0109] Calculate the health score based on the normalized data: Current device status value x t The normalized difference is in, is the historical average of historical data. The updated health score formula is:

[0110] S=100-β·d t ,

[0111] Among them, β is a coefficient used to control the sensitivity of the health score to differences.

[0112] Use visual charts to display the real-time status, health score, and trend prediction results of the device. The data visualization tool can be Grafana or D3.js. Grafana can display the operating status of the device in real time. D3.js can generate dynamic charts of the device operating trend.

[0113] The embodiment of the present invention provides a device operation trend prediction method based on big data, which uses an LSTM model to predict the trend of the future state of the device, improves the accuracy of fault prediction, and reduces the downtime of the device. The fault diagnosis model is used to identify the abnormal state of the device in real time, and an early warning is issued for the abnormal state, thereby realizing the automation of fault early warning. At the same time, the utilization efficiency of the device operation data is improved, and the efficient and intelligent management of the device is realized.

[0114] Example 2

[0115] like Figure 2 As shown, another embodiment of the present invention further provides a device operation trend prediction system based on big data, including: a data acquisition module, a data preprocessing module, a trend prediction module, a fault warning module, a health scoring module and a user interaction module.

[0116] The data acquisition module is used to acquire the equipment operation data collected in real time and transmit it to the data preprocessing module for processing;

[0117] The data preprocessing module is used to clean, reduce the dimension and extract features of the collected data to obtain preprocessed data;

[0118] The trend prediction module uses a long short-term memory network model to predict the future operation trend of the equipment on the preprocessed data to obtain a trend prediction result;

[0119] The fault warning module uses a fault diagnosis model to determine the operating status of the equipment in real time, and sends out a warning signal when an abnormality is detected;

[0120] The health scoring module is used to perform health scoring after normalizing the historical trend of the device to obtain a health score;

[0121] The user interaction module is used to visually display the real-time status, trend prediction results and health score of the device.

[0122] Specifically, in this embodiment, the data preprocessing module includes a data cleaning unit and a data dimension reduction unit. The data cleaning unit uses a discrete wavelet transform method to identify and filter noise, and the data dimension reduction unit uses a principal component analysis method to reduce data dimensions.

[0123] Specifically, in this embodiment, the fault warning module uses a fault diagnosis model to determine the operating status of the device in real time, specifically including:

[0124] Set the objective function:

[0125]

[0126] Here λ is a constant used to weigh the regularization term and loss items The importance of. Among them, ω is the weight vector, ||w|| 2 is the square of the second norm of the weight vector, λ is a positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the data set;

[0127] The decision function is used to determine whether the equipment is operating normally. The decision function is:

[0128] f(x)=sign(w·x+b);

[0129] Wherein, x is an input vector, when f(x)>0, the device operates normally, and when f(x)≤0, a fault warning is triggered. Specifically, in this embodiment, the health scoring module includes a normalization processing unit and a scoring unit, the normalization processing unit finds the maximum and minimum values ​​according to the historical trend data sequence of the device, calculates the average value of the historical data, normalizes the historical trend data to the interval of [0, 1], and calculates the difference value of the current device state value after normalization; the scoring unit is used to calculate the device health score according to the health scoring formula and the difference value.

[0130] In this embodiment, the system also includes a data storage module, which is used to store processed equipment operation data to support historical data query and trend analysis. Data storage type: NoSQL database (such as MongoDB) is used to store unstructured data, and MySQL is used to store structured data. Index by timestamp and equipment number to ensure fast response of data retrieval.

[0131] The embodiment of the present invention provides a big data-based equipment operation trend prediction system, which uses the LSTM model to predict the trend of the future state of the equipment, improves the accuracy of fault prediction, and reduces equipment downtime. The fault diagnosis model is used to identify the abnormal state of the equipment in real time, and an early warning is issued for the abnormal state, realizing the automation of fault early warning. At the same time, it also improves the utilization efficiency of equipment operation data, and realizes efficient and intelligent equipment management.

[0132] Example 3

[0133] like Figure 3 As shown, a structural block diagram of an electronic device according to another embodiment of the present invention, the device includes a processor, an input device, an output device and a memory, the processor is connected to the input device, the output device and the memory respectively, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method described in the first embodiment above.

[0134] It should be understood that in the embodiments of the present invention, the processor referred to may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0135] Input devices may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and output devices may include a display (LCD, etc.), a speaker, etc.

[0136] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0137] In a specific implementation, the processor, input device, and output device described in the embodiments of the present invention may execute the implementation described in the method embodiment provided in the embodiments of the present invention, or may execute the implementation described in the system embodiment described in the embodiments of the present invention, which will not be described in detail here.

[0138] Example 4

[0139] Another embodiment of the present invention further provides an embodiment of a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method described in the first embodiment.

[0140] The computer-readable storage medium may be an internal storage unit of the terminal described in the foregoing embodiments, such as a hard disk or memory of the terminal. The computer-readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit of the terminal and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0141] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the terminals and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0143] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0144] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting equipment operation trends based on big data, characterized in that: The following steps are involved: Obtain real-time collected equipment operation data; Clean, reduce dimension and extract features of the acquired data to obtain preprocessed data; The long short-term memory network model is used to predict the future operation trend of the equipment based on the preprocessed data to obtain the trend prediction results; Use fault diagnosis models to determine the operating status of equipment in real time, and issue warning signals when abnormalities are detected; Generate equipment health scores based on trend prediction results; Visualize the real-time status, trend prediction results and health score of the equipment.

2. The equipment operation trend prediction method based on big data according to claim 1 is characterized in that: The specific methods for cleaning and reducing the dimension of the acquired data include: Discrete wavelet transform method is used to identify and filter noise; Principal component analysis was used to reduce the data dimension.

3. The equipment operation trend prediction method based on big data according to claim 1 is characterized in that: The specific method of using the fault diagnosis model to judge the operating status of the equipment in real time includes: Set the objective function: where ω is the weight vector, ||w|| 2 is the square of the second norm of the weight vector, λ is a positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the data set; The decision function is used to determine whether the equipment is operating normally. The decision function is: f(x)=sign(w·x+b); Where x is the input vector. When f(x)>0, the device operates normally. When f(x)≤0, a fault warning is triggered.

4. The equipment operation trend prediction method based on big data according to claim 1 is characterized in that: The specific method for generating a device health score according to the trend prediction result includes: Find the maximum and minimum values ​​based on the historical trend data sequence of the device, and calculate the average value of the historical data; Normalize historical trend data to the interval of [0, 1]; Calculate the difference value of the current device status value after normalization; The device health score is calculated based on the health score formula and the difference value.

5. A big data-based equipment operation trend prediction system, characterized in that: include: Data acquisition module, data preprocessing module, trend prediction module, fault warning module, health scoring module and user interaction module, The data acquisition module is used to acquire the equipment operation data collected in real time and transmit it to the data preprocessing module for processing; The data preprocessing module is used to clean, reduce the dimension and extract features of the collected data to obtain preprocessed data; The trend prediction module uses a long short-term memory network model to predict the future operation trend of the equipment on the preprocessed data to obtain a trend prediction result; The fault warning module uses a fault diagnosis model to determine the operating status of the equipment in real time, and sends out a warning signal when an abnormality is detected; The health scoring module is used to perform health scoring after normalizing the historical trend of the device to obtain a health score; The user interaction module is used to visually display the real-time status, trend prediction results and health score of the device.

6. The equipment operation trend prediction system based on big data according to claim 5 is characterized in that: The data preprocessing module includes a data cleaning unit and a data dimension reduction unit. The data cleaning unit uses a discrete wavelet transform method to identify and filter noise, and the data dimension reduction unit uses a principal component analysis method to reduce data dimensions.

7. The equipment operation trend prediction system based on big data according to claim 5 is characterized in that: The fault warning module uses a fault diagnosis model to determine the operating status of the equipment in real time, specifically including: Set the objective function: where ω is the weight vector, ||w|| 2 is the square of the second norm of the weight vector, λ is a positive penalty parameter, ξ i is the slack variable, b is the bias term, and i is the number of samples in the data set; The decision function is used to determine whether the equipment is operating normally. The decision function is: f(x)=sign(w·x+b); Where x is the input vector. When f(x)>0, the device operates normally. When f(x)≤0, a fault warning is triggered.

8. The equipment operation trend prediction system based on big data according to claim 5 is characterized in that: The health scoring module includes a normalization processing unit and a scoring unit. The normalization processing unit finds the maximum and minimum values ​​according to the historical trend data sequence of the device, calculates the average value of the historical data, normalizes the historical trend data to the interval of [0, 1], and calculates the difference value of the current device status value after normalization processing; The scoring unit is used to calculate the device health score according to the health scoring formula and the difference value.

9. An electronic device, characterized in that: It includes a processor, an input device, an output device and a memory, the processor is connected to the input device, the output device and the memory respectively, the memory is used to store a computer program, the computer program includes program instructions, and is characterized in that the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 4.

Images