An abnormal monitoring system for production workshops based on the Internet of Things

Abstract

The present invention discloses an abnormal monitoring system for a production workshop based on the Internet of Things, which belongs to the field of production prevention and control technology. The system includes a data acquisition device that collects the operation information of different equipment in the production workshop, including: current information, voltage information, temperature information and infrared image information; the Internet of Things transmission device uploads the equipment operation information to the Internet of Things monitoring platform at a preset frequency; the Internet of Things monitoring platform displays the uploaded equipment operation information in real time, and analyzes and predicts whether the equipment in the production workshop fails based on the equipment operation information. If so, an early warning prompt is given based on the prediction result and an early warning report is sent to the mobile terminal. The failure result of the production equipment is obtained by analyzing and predicting the monitoring data of the real-time production workshop equipment, thereby improving maintenance efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things data monitoring, and more specifically to an abnormality monitoring system for a production workshop based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, more and more companies are beginning to apply Internet of Things technology to production workshops to improve production efficiency, reduce costs and improve product quality.

[0003] However, the traditional abnormal monitoring system of production workshops is usually based on manual inspections and simple sensor monitoring, which cannot achieve real-time and comprehensive abnormal monitoring and early warning. The traditional abnormal monitoring system of production workshops only judges the good or bad running of equipment by thresholds, lacks the use of intelligent analysis technology to mine and analyze equipment operation data and predict fault trends. In addition, due to the large number of types of operation and maintenance equipment in the production workshop and the complexity of the equipment, it is not conducive to finding the key factors that cause equipment operation failures, making its equipment maintenance efficiency low. Summary of the invention

[0004] In view of this, the present invention provides a production workshop abnormality monitoring system based on the Internet of Things, which is used to solve the above-mentioned prior art

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] An abnormal monitoring system for a production workshop based on the Internet of Things, comprising: a data acquisition device, an Internet of Things transmission device, an Internet of Things monitoring platform and a mobile terminal;

[0007] The data acquisition device collects the operation information of different equipment in the production workshop, including: current information, voltage information, temperature information and infrared image information;

[0008] The IoT transmission device uploads the device operation information to the IoT monitoring platform at a preset frequency;

[0009] The IoT monitoring platform displays the uploaded equipment operation information in real time, and analyzes and predicts whether the equipment in the production workshop has a fault based on the equipment operation information. If so, an early warning prompt is issued and an early warning report is sent to the mobile terminal.

[0010] Preferably, the data acquisition device comprises:

[0011] The current sensor, voltage sensor, temperature sensor and infrared camera collect current information, voltage information, temperature information and infrared image information respectively.

[0012] Preferably, the Internet of Things transmission equipment includes:

[0013] A storage module for caching the device operation information;

[0014] The frequency adjustment module sends a driving signal according to a preset frequency, wherein the preset frequency includes:

[0015] Default upload frequency:

[0016]

[0017] Where, σ is the time standard deviation, ω is the preset standard deviation weight, σ0 is the preset standard deviation reference value, and f0 is the standard upload frequency of the upload module used;

[0018] When it is determined that the cached device information is greater than 80% of the total cache capacity, increase the upload frequency:

[0019] f b =Wlog2(1+S / N);

[0020] Where W is the maximum channel bandwidth of the upload module used by the channel, S is the average power of the signal transmitted in the channel, and N is the Gaussian noise power inside the channel;

[0021] An uploading module uploads the device operation information to the Internet of Things monitoring and control platform based on the driving signal.

[0022] Preferably, the Internet of Things monitoring platform includes:

[0023] Display module, which displays the uploaded equipment operation information in real time;

[0024] A prediction module, which analyzes and predicts whether the equipment in the production workshop will fail based on the equipment operation information and generates a corresponding early warning report;

[0025] The early warning module issues an early warning prompt and sends an early warning report to the mobile terminal when a failure occurs in the production workshop equipment.

[0026] Preferably, the prediction module comprises:

[0027] Preprocessing the equipment operation information includes: obtaining historical voltage information, historical current information, and historical temperature information of different equipment in the production workshop, and performing feature extraction to generate a spectrum graph feature sample data set; obtaining historical infrared image information of different equipment in the production workshop, and performing feature extraction to generate an infrared image feature sample data set; and dividing the spectrum graph feature sample data set and the infrared image feature sample data set into a training set, a test set, and a prediction set, respectively;

[0028] Build a neural network model and input training set and test set data for learning and training;

[0029] The equipment operation information is preprocessed, and the trained neural network model is called to perform multi-scale fault identification to obtain the prediction results.

[0030] Preferably, the data format of the generated spectrum graph feature sample data set is:

[0031] α=[(x1,y1),(x2,y2),…,(x n ,y n )];

[0032] In the formula, x1, x2…x n is the equipment running time, y1,y2…y n The spectrum diagram corresponding to the running time.

[0033] Preferably, the data format of the generated infrared image feature sample data set is:

[0034] β=[(u1,w1),(u2,w2),…,(u m ,w m )];

[0035] In the formula, u1,u2…u m is the equipment running time, w1,w2…w m is the infrared image corresponding to the running time.

[0036] Preferably, the neural network model is constructed, and the training set and test set data are input for learning and training, including: a convolution layer, a pooling layer, and a fully connected layer, wherein the convolution layer iteratively extracts features of training sets at different levels, and after passing through the pooling layer, the prediction result is obtained through the fully connected layer, and the loss function is calculated based on the prediction result output, the parameter weights of the neural network model are updated, and the Adam algorithm is used for optimization training to obtain a trained neural network model.

[0037] Preferably, the device operation information is preprocessed, and a trained neural network model is called to perform multi-scale fault identification to obtain a prediction result, including:

[0038] The equipment operation information is cleaned, denoised by wavelet packets and normalized:

[0039] Extracting the frequency spectrum features of the voltage information, current information and temperature information in the equipment operation information, and obtaining a frequency spectrum feature input set in the same data format as the frequency spectrum feature sample data set;

[0040] Extracting infrared image features from the equipment operation information, and obtaining an infrared image feature input set in the same data format as the infrared image feature sample data set;

[0041] The frequency spectrum feature input set and the infrared image feature input set are respectively input into the trained neural network model to obtain a prediction result.

[0042] Preferably, the Internet of Things monitoring platform also includes: a control module, which controls the start and stop of corresponding equipment based on the prediction results.

[0043] Through the above technical solution, the present invention has the following beneficial effects compared with the prior art:

[0044] 1) The present invention realizes low-power uploading through different uploading frequencies in the Internet of Things transmission device, and improves the reliability of data collection through caching;

[0045] 2) Through the collection and processing of multi-dimensional data and the use of deep learning to build a neural network model, the changing patterns of various monitoring data can be quickly, accurately and batch-wise intelligently identified through the real-time collected spectrum feature data and infrared image feature data. It is especially suitable for the rapid batch management of large amounts of monitoring data in production workshops, thereby improving equipment maintenance efficiency.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0049] Figure 2 This is a schematic diagram of the structure of the Internet of Things transmission device of the present invention;

[0050] Figure 3 It is a schematic diagram of the structure of the Internet of Things monitoring platform of the present invention. DETAILED DESCRIPTION

[0051] The following is a further description of a production workshop abnormality monitoring system based on the Internet of Things of the present invention in conjunction with the accompanying drawings and specific embodiments.

[0052] See also Figure 1 , the embodiment of the present invention discloses a production workshop abnormality monitoring system based on the Internet of Things, including: a data acquisition device, an Internet of Things transmission device, an Internet of Things monitoring platform and a mobile terminal;

[0053] The data collection device collects the operation information of different equipment in the production workshop, including:

[0054] The current sensor, voltage sensor, temperature sensor and infrared camera collect current information, voltage information, temperature information and infrared image information respectively.

[0055] Specifically, the IoT transmission device uploads the device operation information to the IoT monitoring platform at a preset frequency. Figure 2 , IoT transmission equipment specifically includes:

[0056] A storage module for caching the device operation information;

[0057] The frequency adjustment module sends a driving signal according to a preset frequency, wherein the preset frequency includes:

[0058] Default upload frequency:

[0059]

[0060] Where, σ is the time standard deviation, ω is the preset standard deviation weight, σ0 is the preset standard deviation reference value, and f0 is the standard upload frequency of the upload module used;

[0061] When it is determined that the cached device information is greater than 80% of the total cache capacity, increase the upload frequency:

[0062] f b =Wlog2(1+S / N);

[0063] Where W is the maximum channel bandwidth of the upload module used by the channel, S is the average power of the signal transmitted in the channel, and N is the Gaussian noise power inside the channel;

[0064] An uploading module uploads the device operation information to the Internet of Things monitoring and control platform based on the driving signal.

[0065] Specifically, the IoT monitoring platform displays the uploaded equipment operation information in real time, and analyzes and predicts whether the equipment in the production workshop has a fault based on the equipment operation information. If so, an early warning prompt is issued and an early warning report is sent to the mobile terminal. Please refer to Figure 3 , the IoT monitoring platform specifically includes:

[0066] Display module, which displays the uploaded equipment operation information in real time;

[0067] A prediction module, which analyzes and predicts whether the equipment in the production workshop will fail based on the equipment operation information and generates a corresponding early warning report;

[0068] The early warning module issues an early warning prompt and sends an early warning report to the mobile terminal when a failure occurs in the production workshop equipment.

[0069] Specifically, the prediction module includes:

[0070] Preprocessing the equipment operation information includes: obtaining historical voltage information, historical current information, and historical temperature information of different equipment in the production workshop, and performing feature extraction to generate a spectrum graph feature sample data set; obtaining historical infrared image information of different equipment in the production workshop, and performing feature extraction to generate an infrared image feature sample data set; and dividing the spectrum graph feature sample data set and the infrared image feature sample data set into a training set, a test set, and a prediction set, respectively;

[0071] Build a neural network model and input training set and test set data for learning and training;

[0072] The equipment operation information is preprocessed, and the trained neural network model is called to perform multi-scale fault identification to obtain the prediction results.

[0073] Specifically, the data format of the generated spectrum graph feature sample data set is:

[0074] α=[(x1,y1),(x2,y2),…,(x n ,y n )];

[0075] In the formula, x1, x2…x n is the equipment running time, y1,y2…y n The spectrum diagram corresponding to the running time.

[0076] Specifically, the data format of the generated infrared image feature sample data set is:

[0077] β=[(u1,w1),(u2,w2),…,(u m ,w m )];

[0078] In the formula, u1,u2…u m is the equipment running time, w1,w2…w m is the infrared image corresponding to the running time.

[0079] Specifically, a neural network model is constructed, and training set and test set data are input for learning and training, including: convolution layer, pooling layer and fully connected layer. The convolution layer is used to iteratively extract features at different levels, and the pooling layer is used to reduce network parameters and reduce overfitting. After three sets of convolution and pooling, a fully connected layer network is input to obtain classification output, and the loss function is calculated according to the classification output. The update gradient is calculated based on the loss function. After the network weights are updated, the Adam algorithm is used for optimization training to obtain a trained neural network model.

[0080] Specifically, the equipment operation information is preprocessed, and the trained neural network model is called to perform multi-scale fault identification to obtain prediction results, including:

[0081] The equipment operation information is cleaned, denoised by wavelet packets and normalized:

[0082] Extracting the frequency spectrum features of the voltage information, current information and temperature information in the equipment operation information, and obtaining a frequency spectrum feature input set in the same data format as the frequency spectrum feature sample data set;

[0083] Extracting infrared image features from the equipment operation information, and obtaining an infrared image feature input set in the same data format as the infrared image feature sample data set;

[0084] The frequency spectrum feature input set and the infrared image feature input set are respectively input into the trained neural network model to obtain a prediction result.

[0085] Specifically, the IoT monitoring platform also includes: a control module that controls the start and stop of corresponding equipment based on the prediction results.

[0086] More specifically, the key factors affecting equipment operation failures are analyzed based on the prediction results, and combined with the equipment maintenance plan, guidance is provided for the preventive maintenance of the equipment.

[0087] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An abnormal monitoring system for production workshops based on the Internet of Things, It is characterized in that include: Data collection equipment, IoT transmission equipment, IoT monitoring platform and mobile terminals; The data acquisition device collects the operation information of different equipment in the production workshop, including: current information, voltage information, temperature information and infrared image information; The IoT transmission device uploads the device operation information to the IoT monitoring platform at a preset frequency; The IoT monitoring platform displays the uploaded equipment operation information in real time, and analyzes and predicts whether the equipment in the production workshop has a fault based on the equipment operation information. If so, an early warning prompt is issued based on the prediction result and an early warning report is sent to the mobile terminal; Wherein, the Internet of Things monitoring platform includes: Display module, which displays the uploaded equipment operation information in real time; A prediction module, which analyzes and predicts whether the equipment in the production workshop will fail based on the equipment operation information and generates a corresponding early warning report; An early warning module, which issues an early warning prompt based on the prediction result and sends an early warning report to the mobile terminal; The prediction module comprises: Obtain historical voltage information, historical current information, and historical temperature information of different equipment in the production workshop, perform feature extraction, and generate a spectrum feature sample data set; obtain historical infrared image information of different equipment in the production workshop, perform feature extraction, and generate an infrared feature sample data set; and divide the spectrum feature sample data set and the infrared feature sample data set into a training set, a test set, and a prediction set respectively; Build a neural network model and input training set and test set data for learning and training; Preprocess the equipment operation information and call the trained neural network model for multi-scale fault identification to obtain the prediction results; The Internet of Things transmission equipment includes: A storage module for caching the device operation information; The frequency adjustment module sends a driving signal according to a preset frequency, wherein the preset frequency includes: Default upload frequency: In the formula, is the time standard deviation, is the preset standard deviation weight, is the preset standard deviation reference value, The standard upload frequency for the upload module used; When the cached device information is greater than 80% of the total cache capacity, increase the upload frequency: In the formula, is the maximum channel bandwidth of the upload module used by the channel, S is the average power of the signal transmitted in the channel, and N is the Gaussian noise power inside the channel; An uploading module uploads the device operation information to the Internet of Things monitoring platform based on the driving signal.

2. According to the Internet of Things-based production workshop abnormality monitoring system according to claim 1, It is characterized in that The data acquisition device comprises: The current sensor, voltage sensor, temperature sensor and infrared camera collect current information, voltage information, temperature information and infrared image information respectively.

3. According to the Internet of Things-based production workshop abnormality monitoring system of claim 1, It is characterized in that The data format of the generated spectrum graph feature sample data set is: In the formula, is the equipment running time, The spectrum diagram corresponding to the running time.

4. According to the Internet of Things-based production workshop abnormality monitoring system of claim 1, It is characterized in that The data format of the generated infrared image feature sample data set is: In the formula, is the equipment running time, is the infrared image corresponding to the running time.

5. According to the Internet of Things-based production workshop abnormality monitoring system of claim 1, It is characterized in that The neural network model is constructed, and the training set and test set data are input for learning and training, including: a convolution layer, a pooling layer, and a fully connected layer, wherein the convolution layer iteratively extracts features of training sets at different levels, and after passing through the pooling layer, a prediction result is obtained through the fully connected layer, and a loss function is calculated based on the prediction result output, the parameter weights of the neural network model are updated, and the Adam algorithm is used for optimization training to obtain a trained neural network model.

6. According to the Internet of Things-based production workshop abnormality monitoring system of claim 1, It is characterized in that The equipment operation information is preprocessed, and the trained neural network model is called to perform multi-scale fault identification to obtain prediction results, including: The equipment operation information is cleaned, denoised by wavelet packets and normalized: Extracting the frequency spectrum features of the voltage information, current information and temperature information in the equipment operation information, and obtaining a frequency spectrum feature input set in the same data format as the frequency spectrum feature sample data set; Extracting infrared image features from the equipment operation information, and obtaining an infrared image feature input set in the same data format as the infrared image feature sample data set; The frequency spectrum feature input set and the infrared image feature input set are respectively input into the trained neural network model to obtain a prediction result.

7. According to claim 1, a production workshop abnormality monitoring system based on the Internet of Things, It is characterized in that The Internet of Things monitoring platform also includes: a control module, which controls the start and stop of corresponding equipment based on the prediction results.

Images