Mine lamp production management and control method based on deep learning and related equipment

Abstract

The invention provides a mining lamp production management and control method based on deep learning and related equipment. The method comprises the steps of collecting parameter data in a mine lamp production environment based on a preset sensor in a production process of a target mine lamp; preprocessing the parameter data to obtain corresponding target parameter data; calling a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data; performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mine lamp; judging whether the quality prediction result is low in quality or not; and if yes, performing corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy. Based on the use of the quality prediction model, the production quality of the miner's lamp can be accurately predicted and monitored, so that the production efficiency and the product quality of the miner's lamp are improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a mining lamp production control method based on deep learning and related equipment. Background Art

[0002] With the rapid development of social economy, the demand for energy is increasing. With the development of mining lamp manufacturers, mining lamps are exported to all over the world as important lighting tools for miners in underground working environments such as coal mines. The quality and performance of mining lamps are directly related to the safety and production efficiency of miners, making modern management of the production control of mining lamps an inevitable requirement.

[0003] However, the existing production control methods of mining lamps mainly rely on manual monitoring and simple automated equipment, which have problems such as low production efficiency and unstable quality. Summary of the invention

[0004] The main purpose of the present invention is to provide a mining lamp production control method and related equipment based on deep learning, aiming to solve the technical problems that the mining lamp production control method in the prior art mainly relies on manual monitoring and simple automated equipment, and has low production efficiency and unstable quality.

[0005] To achieve the above object, the present invention provides a mining lamp production control method based on deep learning, the method comprising:

[0006] During the production process of the target mining lamp, parameter data in the mining lamp production environment is collected based on preset sensors;

[0007] Preprocessing the parameter data to obtain corresponding target parameter data;

[0008] Calling a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data;

[0009] Performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp;

[0010] Determining whether the quality prediction result is of low quality;

[0011] If so, the parameter data is adjusted accordingly based on a preset parameter adjustment strategy.

[0012] Optionally, before calling the preset quality prediction model, the method further includes:

[0013] Acquiring production parameter data corresponding to a finished miner's lamp, and acquiring historical quality inspection data corresponding to the finished miner's lamp;

[0014] Constructing corresponding sample data based on the production parameter data and the historical quality inspection data;

[0015] Dividing the sample data into a training data set and a validation data set;

[0016] Using the training data set to train the deep learning model to obtain a corresponding first model;

[0017] Performing a performance evaluation on the first model based on the validation data set to obtain a second model that meets preset performance conditions;

[0018] The second model is used as the quality prediction model.

[0019] Optionally, the performing corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy includes:

[0020] Obtaining correlation results between each of the parameter data and the quality prediction results;

[0021] Filtering out key parameters from all the parameter data based on the correlation results;

[0022] Obtaining a specified parameter adjustment strategy corresponding to the key parameter;

[0023] The key parameters are adjusted accordingly based on the specified parameter adjustment strategy.

[0024] Optionally, the obtaining of the correlation results between each of the parameter data and the quality prediction result includes:

[0025] Get multiple preset statistical algorithms;

[0026] Selecting a target statistical algorithm from all the statistical algorithms;

[0027] Calculating a correlation score between the specified parameter data and the quality prediction result based on the target statistical algorithm; wherein the specified parameter data is any one parameter among all the parameter data;

[0028] The correlation score is used as a specified correlation result between the specified parameter data and the quality prediction result.

[0029] Optionally, the preprocessing the parameter data to obtain corresponding target parameter data includes:

[0030] Performing data cleaning processing on the parameter data to obtain corresponding first parameter data;

[0031] Performing data normalization processing on the first parameter data to obtain corresponding second parameter data;

[0032] Performing format conversion processing on the second parameter data to obtain corresponding third parameter data;

[0033] The third parameter data is used as the target parameter data.

[0034] Optionally, after preprocessing the parameter data to obtain corresponding target parameter data, the method further includes:

[0035] Call the preset data buffer;

[0036] Obtaining a preset data transmission strategy;

[0037] Based on the data transmission strategy, the target parameter data is stored in the data buffer area.

[0038] Optionally, after performing corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy, the method further includes:

[0039] Displaying the quality prediction result on a preset monitoring screen;

[0040] Generate corresponding warning information based on the quality prediction result;

[0041] Obtain communication information of relevant personnel;

[0042] Based on the communication information, the warning information is sent to the relevant personnel.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a mining lamp production control device based on deep learning, and the mining lamp production control device based on deep learning includes:

[0044] The acquisition module is used to collect parameter data in the production environment of the mining lamp based on preset sensors during the production process of the target mining lamp;

[0045] A preprocessing module, used for preprocessing the parameter data to obtain corresponding target parameter data;

[0046] A first calling module is used to call a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data;

[0047] A prediction module, used for performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp;

[0048] A judgment module, used to judge whether the quality prediction result is of low quality;

[0049] The adjustment module is used to, if yes, perform corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy.

[0050] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0051] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the deep learning-based mining lamp production control methods proposed in the embodiments of the present application are implemented.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0053] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the deep learning-based mining lamp production control methods proposed in the embodiments of the present application are implemented.

[0054] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0055] The present invention provides a deep learning-based mining lamp production control method and related equipment, the method comprising: in the production process of the target mining lamp, firstly, based on a preset sensor, the parameter data in the mining lamp production environment is collected; and the parameter data is preprocessed to obtain the corresponding target parameter data; then a preset quality prediction model is called; wherein the quality prediction model is a model generated after training a preset deep learning model based on pre-constructed sample data; then, the target parameter data is predicted and processed based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp; subsequently, it is determined whether the quality prediction result is of low quality; if so, the parameter data is adjusted accordingly based on a preset parameter adjustment strategy. The present invention collects parameter data in the mining lamp production environment based on the use of preset sensors in the production process of the target mining lamp, and preprocesses the parameter data to obtain the corresponding target parameter data, and then predicts and processes the target parameter data based on the use of the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp, thereby automatically and accurately realizing real-time prediction and monitoring of the production quality of the mining lamp. When the quality prediction result is detected to be low quality, the parameter data will be adjusted accordingly based on the use of parameter adjustment strategy, so that quality problems in the production process of mining lamps can be automatically and intelligently discovered and solved, thereby effectively improving the production efficiency and product quality of mining lamps. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0058] Figure 2 It is a flow chart of a mining lamp production control method based on deep learning provided by an embodiment of the present invention;

[0059] Figure 3 It is a structural schematic diagram of an embodiment of a mining lamp production control device based on deep learning according to the present application;

[0060] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0061] The deep learning-based mining lamp production control method provided by the embodiment of the present invention is applied to the deep learning-based mining lamp production control device. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned figures are used to distinguish different objects, not to describe a specific order.

[0062] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0064] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0065] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0066] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0067] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0068] It should be noted that the deep learning-based mining lamp production control method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the deep learning-based mining lamp production control device is generally set in the server / terminal device.

[0069] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0070] With the rapid development of social economy, the demand for energy is increasing. With the development of mining lamp manufacturers, mining lamps are exported to all over the world as important lighting tools for miners in underground working environments such as coal mines. The quality and performance of mining lamps are directly related to the safety and production efficiency of miners, making modern management of the production control of mining lamps an inevitable requirement.

[0071] However, the existing production control methods of mining lamps mainly rely on manual monitoring and simple automated equipment, which have problems such as low production efficiency and unstable quality.

[0072] Continue to refer Figure 2 , shows a flow chart of an embodiment of a mining lamp production control method based on deep learning proposed in this application. The embodiment of this application can acquire and process relevant data based on artificial intelligence technology.

[0073] The deep learning-based mining lamp production control method provided by the embodiment of the present invention comprises the following steps:

[0074] S210, during the production process of the target mining lamp, parameter data in the mining lamp production environment is collected based on preset sensors.

[0075] In this step, the present invention can be applied to the business scenario of controlling the production of miner's lamps in the field of miner's lamp production, and the execution subject of the present invention can be specifically a miner's lamp production control system, or simply referred to as a system. Among them, various sensors (such as temperature sensors, humidity sensors, gas concentration sensors, etc.) are pre-set in various links of miner's lamp production. In the process of miner's lamp production, these sensors can actually collect parameter data in the miner's lamp production environment, such as raw material quality, production environment temperature, humidity, gas concentration, operating status of production equipment and other parameters.

[0076] S220, preprocessing the parameter data to obtain corresponding target parameter data.

[0077] In this step, the specific implementation process of preprocessing the parameter data to obtain the corresponding target parameter data will be further described in detail in the subsequent specific embodiments of the present invention, and will not be elaborated on here.

[0078] S230, calling a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data.

[0079] In this step, the specific construction process of the above-mentioned quality prediction model will be further described in detail in the subsequent specific embodiments of the present invention, and will not be elaborated in detail here.

[0080] S240, performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp.

[0081] In this step, the target parameter data can be input into the quality prediction model to perform forward propagation calculation to obtain the corresponding prediction results. Specifically, it usually includes calculating the probability distribution of high quality and low quality, and then judging the production quality of the miner's lamp based on a certain probability threshold (such as 0.5). If the obtained probability distribution is greater than or equal to the above probability threshold, the production quality of the miner's lamp is judged to be high quality, and a quality prediction result with high quality content is generated. If the obtained probability distribution is less than the above probability threshold, the production quality of the miner's lamp is judged to be low quality, and a quality prediction result with low quality content is generated.

[0082] S250: Determine whether the quality prediction result is of low quality.

[0083] In this step, the content of the quality prediction result may include high quality or low quality. The content of the quality prediction result may be analyzed to identify whether the content of the quality prediction result is of low quality. If the content of the quality prediction result is of high quality, it indicates that the production quality of the target mining lamp meets the quality production standard of the mining lamp, and there is no need to adjust the parameter data in the mining lamp production environment in the future.

[0084] S260: If yes, perform corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy.

[0085] In this step, the specific implementation process of the above-mentioned corresponding adjustment processing of the parameter data based on the preset parameter adjustment strategy will be further described in detail in the subsequent specific embodiments of the present invention, and will not be elaborated in detail here.

[0086] In an embodiment of the present invention, during the production process of a target miner's lamp, firstly, parameter data in the production environment of the miner's lamp is collected based on a preset sensor; and the parameter data is preprocessed to obtain corresponding target parameter data; then a preset quality prediction model is called; wherein the quality prediction model is a model generated after training a preset deep learning model based on pre-constructed sample data; then, the target parameter data is predicted and processed based on the quality prediction model to obtain a quality prediction result corresponding to the target miner's lamp; subsequently, it is determined whether the quality prediction result is of low quality; if so, the parameter data is adjusted accordingly based on a preset parameter adjustment strategy. The present invention collects parameter data in the production environment of the miner's lamp based on the use of preset sensors during the production process of the target miner's lamp, and preprocesses the parameter data to obtain corresponding target parameter data, and then predicts and processes the target parameter data based on the use of the quality prediction model to obtain a quality prediction result corresponding to the target miner's lamp, thereby automatically and accurately realizing real-time prediction and monitoring of the production quality of the miner's lamp. When the quality prediction result is detected to be low quality, the parameter data will be adjusted accordingly based on the use of parameter adjustment strategy, so that quality problems in the production process of mining lamps can be automatically and intelligently discovered and solved, thereby effectively improving the production efficiency and product quality of mining lamps.

[0087] Optionally, before calling the preset quality prediction model, the method further includes:

[0088] Acquire production parameter data corresponding to the finished miner's lamp, and acquire historical quality inspection data corresponding to the finished miner's lamp.

[0089] In this step, the above-mentioned sensors (such as temperature sensors, humidity sensors, gas concentration sensors, etc.) are used in advance to collect the production parameter data of the above-mentioned finished miner's lamp during the production process, for example, data such as raw material quality, production environment temperature, humidity, gas concentration, and operating status of production equipment. The above-mentioned historical quality inspection data may include the quality inspection report of the finished miner's lamp and the corresponding user feedback data. Among them, the quality inspection report of the above-mentioned finished miner's lamp may include the test results of key indicators such as brightness, battery life, and waterproof performance. In addition, user feedback on the quality of the finished miner's lamp can be collected through market research, user surveys, etc., including problems and satisfaction during use, so as to obtain user feedback data. Subsequently, the quality inspection report and user feedback data are integrated to form a complete historical quality inspection data of the finished miner's lamp.

[0090] Corresponding sample data is constructed based on the production parameter data and the historical quality inspection data.

[0091] In this step, the above-mentioned production parameter data are labeled by using the above-mentioned historical quality inspection data as labels of the corresponding production parameter data, so as to construct the required sample data.

[0092] The sample data is divided into a training data set and a validation data set.

[0093] In this step, the sample data may be divided into corresponding training data sets and verification data sets according to a preset data division ratio. There is no limitation on the numerical value of the data division ratio, for example, 7:3 may be used.

[0094] The deep learning model is trained using the training data set to obtain a corresponding first model.

[0095] In this step, the structure of the matching deep learning model can be pre-set according to the data characteristics of the collected production parameter data of the miner's lamp and the requirements of the miner's lamp quality prediction task. Specifically, the deep learning model may include an input layer, a hidden layer, and an output layer. Among them, the input layer can be designed according to the dimension and type of the production parameter data of the miner's lamp to ensure that the original data can be received and processed; the hidden layer can be designed according to the model structure and the task requirements of the miner's lamp quality prediction task, including a convolutional layer, a pooling layer, a fully connected layer, etc.; the output layer can be designed according to the task requirements of the miner's lamp quality prediction task, such as using a Softmax function to output the probability distribution of high quality and low quality. In addition, models such as convolutional neural networks (CNN) and recurrent neural networks (RNN) can also be directly used as the above-mentioned deep learning models.

[0096] Specifically, the process of training the deep learning model using the above training data set includes: setting hyperparameters such as learning rate, batch size, and number of iterations according to the model structure of the deep learning model and the task requirements of the mining lamp quality prediction task. Then, the deep learning model is trained using the above training data set, and the model parameters are optimized by the back propagation algorithm to obtain a trained first model. In the training process, the model weights and training logs are regularly saved for subsequent analysis and tuning.

[0097] A performance evaluation is performed on the first model based on the validation data set to obtain a second model that meets preset performance conditions.

[0098] In this step, the first model can be evaluated by using the validation data set, including the calculation of accuracy, recall, F1 score and other indicators, and then the model structure and hyperparameters can be adjusted according to the validation set evaluation results to optimize the performance of the first model until a second model that meets the preset performance conditions (for example, the evaluation index is greater than the specified index threshold) is obtained.

[0099] The second model is used as the quality prediction model.

[0100] In this step, the quality prediction model obtained is a model that can accurately predict the production quality of the mining lamp.

[0101] In an embodiment of the present invention, by obtaining production parameter data corresponding to a finished miner's lamp and obtaining historical quality inspection data corresponding to the finished miner's lamp; then constructing corresponding sample data based on the production parameter data and the historical quality inspection data; then dividing the sample data into a training data set and a verification data set; subsequently using the training data set to train the deep learning model to obtain a corresponding first model; finally, based on the verification data set, the performance of the first model is evaluated to obtain a second model that meets the preset performance conditions, and the second model is used as the quality prediction model. The present invention obtains production parameter data corresponding to a finished miner's lamp and obtains historical quality inspection data corresponding to the finished miner's lamp, then constructs corresponding sample data based on the production parameter data and the historical quality inspection data, and divides the sample data into a training data set and a verification data set, and then trains and performs performance evaluation on the deep learning model based on the use of the training data set and the verification data set, thereby efficiently and accurately obtaining a quality prediction model that meets the performance conditions, effectively improving the model construction efficiency of the quality prediction model, and ensuring the prediction effect of the obtained quality prediction model. It is beneficial to the subsequent use of the quality prediction model to accurately predict and monitor the production quality of the miner's lamp, thereby improving the production efficiency and product quality of the miner's lamp.

[0102] Optionally, the performing corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy includes:

[0103] Obtain the correlation results between each of the parameter data and the quality prediction results.

[0104] In this step, the specific implementation process of obtaining the correlation results between each of the parameter data and the quality prediction results will be further described in detail in the subsequent specific embodiments of the present invention, and will not be elaborated on here.

[0105] Key parameters are screened out from all the parameter data based on the correlation results.

[0106] In this step, the correlation results can be numerically compared to select the specified number of specific correlation results with the highest values ​​from all the correlation results, and the specific parameter data corresponding to the specific correlation results can be obtained, and the specific parameter data can be used as the key parameters. There is no specific limitation on the selection of the values ​​of the specified number, for example, 1 or 2 can be used. In addition, the key parameters are the parameter data with the highest correlation with the quality prediction results. Exemplarily, the key parameters may include the temperature of the production equipment, or may also include the speed of the production equipment.

[0107] Obtain a specified parameter adjustment strategy corresponding to the key parameter.

[0108] In this step, for each key parameter, a specific adjustment strategy is pre-set. For example, if the prediction results show that production quality is affected by equipment temperature, the strategy may be to adjust the temperature setting of the equipment. In addition, the adjustment strategy also includes the adjustment range, adjustment speed, and any necessary monitoring and feedback mechanisms.

[0109] The key parameters are adjusted accordingly based on the specified parameter adjustment strategy.

[0110] In this step, the above-specified parameter adjustment strategy can be converted into implementation steps and timetables in a specific implementation plan, and the implementation plan includes all necessary resources, responsibilities and communication channels. The adjustment of key parameters can be completed by executing the above implementation plan.

[0111] In an embodiment of the present invention, by obtaining the correlation results between each of the parameter data and the quality prediction results; then based on the correlation results, the key parameters are screened out from all the parameter data; then the designated parameter adjustment strategy corresponding to the key parameters is obtained; and then the key parameters are adjusted accordingly based on the designated parameter adjustment strategy. The present invention obtains the correlation results between each of the parameter data and the quality prediction results, and based on the correlation results, the key parameters are screened out from all the parameter data, and then the designated parameter adjustment strategy corresponding to the key parameters is obtained, and then the key parameters are adjusted accordingly based on the designated parameter adjustment strategy. Thus, the key parameters of the target miner's lamp in the generation process can be adjusted in real time according to the quality prediction results output by the quality prediction model for the content of the target parameter data as low quality, thereby optimizing the production process and improving the production quality of the target miner's lamp. This can not only reduce the quality problems in the production process of the miner's lamp, but also improve the production efficiency of the miner's lamp production and reduce the cost of the miner's lamp production, which is conducive to bringing greater economic benefits to the enterprise.

[0112] Optionally, the obtaining of the correlation results between each of the parameter data and the quality prediction result includes:

[0113] Get multiple preset statistical algorithms.

[0114] In this step, the above statistical algorithms may at least include Pearson correlation coefficient, Spearman rank correlation coefficient, principal component analysis, etc.

[0115] A target statistical algorithm is selected from all the statistical algorithms.

[0116] In this step, there is no specific limitation on the selection of the above-mentioned target statistical algorithm, and it can be selected according to actual business needs. Preferably, the statistical quality scores of various statistical algorithms can be compared, and the algorithm with the highest statistical quality score can be used as the above-mentioned target statistical algorithm. Among them, the statistical quality score of the statistical algorithm can be calculated by weighted summing the processing efficiency, algorithm satisfaction and algorithm usage frequency of the statistical algorithm.

[0117] The correlation score between the designated parameter data and the quality prediction result is calculated based on the target statistical algorithm, wherein the designated parameter data is any one parameter among all the parameter data.

[0118] In this step, the correlation score between the above-mentioned specified parameter data and the quality prediction result can be calculated and processed according to the correlation statistical step of the screened target statistical algorithm, so as to obtain the correlation score between the specified parameter data and the quality prediction result.

[0119] The correlation score is used as a specified correlation result between the specified parameter data and the quality prediction result.

[0120] In an embodiment of the present invention, a plurality of preset statistical algorithms are obtained; then a target statistical algorithm is screened out from all the statistical algorithms; then a correlation score between the specified parameter data and the quality prediction result is calculated based on the target statistical algorithm; wherein the specified parameter data is any one parameter among all the parameter data; and the correlation score is subsequently used as the specified correlation result between the specified parameter data and the quality prediction result. The present invention obtains a plurality of preset statistical algorithms, and screens out a target statistical algorithm from all the statistical algorithms, and then calculates the correlation score between the specified parameter data and the quality prediction result based on the use of the target statistical algorithm, so as to efficiently and accurately obtain the specified correlation result between the specified parameter data and the quality prediction result, effectively improving the calculation efficiency of the correlation result between the parameter data and the quality prediction result, and ensuring the data accuracy of the obtained correlation result.

[0121] Optionally, the preprocessing the parameter data to obtain corresponding target parameter data includes:

[0122] The parameter data is cleaned to obtain corresponding first parameter data.

[0123] In this step, the above data cleaning includes removing outliers and filling missing values. Removing outliers includes: removing outliers in parameter data by setting thresholds, using statistical methods, etc. to ensure the accuracy of the data. Filling missing values ​​includes: for missing parameter data, interpolation, mean filling, etc. can be used to fill in to ensure the integrity of the data.

[0124] The first parameter data is subjected to data normalization processing to obtain corresponding second parameter data.

[0125] In this step, a suitable normalization method, such as Min-Max normalization, Z-score normalization, etc., can be selected according to the distribution characteristics of the parameter data to perform data normalization processing on the first parameter data, thereby obtaining the corresponding second parameter data.

[0126] The second parameter data is format converted to obtain corresponding third parameter data.

[0127] In this step, the format conversion process refers to converting the second parameter data into normalized data so as to meet the model input requirements of the quality prediction model.

[0128] The third parameter data is used as the target parameter data.

[0129] In an embodiment of the present invention, the parameter data is cleaned to obtain corresponding first parameter data; the first parameter data is then normalized to obtain corresponding second parameter data; the second parameter data is then format converted to obtain corresponding third parameter data; and the third parameter data is subsequently used as the target parameter data. The present invention performs data cleaning, data normalization, and format conversion on the parameter data, thereby achieving efficient and accurate preprocessing of the parameter data, thereby ensuring the data accuracy and standardization of the obtained target parameter data.

[0130] Optionally, after preprocessing the parameter data to obtain corresponding target parameter data, the method further includes:

[0131] Call the preset data buffer.

[0132] In this step, the data cache area may be a data cache area pre-set locally or in the cloud.

[0133] Get the preset data transfer policy.

[0134] In this step, the above data transmission strategy can specifically adopt a data transmission method corresponding to a wired or wireless communication technology (such as Wi-Fi, Bluetooth, LoRa, etc.).

[0135] Based on the data transmission strategy, the target parameter data is stored in the data buffer area.

[0136] In this step, the pre-processed target parameter data can be stored in the data buffer in real time by using the above data transmission method, so that the temporarily stored target parameter data can be extracted from the data buffer and input into the quality prediction model for prediction processing, which is conducive to reducing data transmission delay and improving prediction efficiency.

[0137] In an embodiment of the present invention, a preset data cache is called; then a preset data transmission strategy is obtained; and subsequently, based on the data transmission strategy, the target parameter data is stored in the data cache. The present invention can ensure that real-time target parameter data can be stored efficiently and accurately by calling a preset data cache and then storing the target parameter data in the data cache based on the obtained data transmission strategy. In addition, by subsequently extracting the temporarily stored target parameter data from the data cache and inputting it into the quality prediction model for prediction processing, the data transmission delay can be effectively reduced and the prediction efficiency of the quality prediction model can be improved.

[0138] Optionally, after performing corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy, the method further includes:

[0139] The quality prediction result is displayed on a preset monitoring screen.

[0140] In this step, the monitoring screen is a pre-built screen for displaying the quality prediction results of the target mining lamp. By displaying the quality prediction results on the monitoring screen in real time, production managers can intuitively understand the quality status of the current production line, which is conducive to improving the work experience of production managers.

[0141] Generate corresponding warning information based on the quality prediction result.

[0142] In this step, the identification information of the target miner's lamp (such as the miner's lamp number) and the quality prediction result corresponding to the target miner's lamp can be filled into the corresponding positions in the preset warning information template, thereby generating warning information matching the target miner's lamp. The template content of the warning information template can be set according to actual business needs, for example, it can include a miner's lamp number area and a prediction result area.

[0143] Get the communication information of relevant personnel.

[0144] In this step, the above-mentioned relevant personnel may refer to management personnel or maintenance personnel related to the production of mining lamps. The above-mentioned communication information may include email addresses, mobile phone numbers, etc.

[0145] Based on the communication information, the warning information is sent to the relevant personnel.

[0146] In this step, the warning information can be automatically sent to the communication terminal corresponding to the relevant personnel based on the communication information obtained from the relevant personnel, so that the relevant personnel can timely understand the current production quality problems of the target mining lamp by referring to the warning information, and then can take corresponding solutions in time to solve the production quality problems of the target mining lamp in the production process, thereby ensuring the product quality of the target mining lamp and improving the production efficiency of the target mining lamp.

[0147] In an embodiment of the present invention, the quality prediction result is displayed on a preset monitoring screen; then corresponding warning information is generated based on the quality prediction result; then the communication information of the relevant personnel is obtained; and subsequently, the warning information is sent to the relevant personnel based on the communication information. When the quality prediction result of the target mining lamp is detected to be low quality, the present invention will automatically display the quality prediction result on a preset monitoring screen, so that the production management personnel can intuitively understand the quality status of the current production line, which is conducive to improving the work experience of the production management personnel. In addition, the corresponding warning information is automatically generated based on the quality prediction result, and the warning information is sent to the relevant personnel based on the acquired communication information of the relevant personnel, so that the relevant personnel can timely understand the current production quality problems of the target mining lamp by consulting the warning information, and then can timely take corresponding solutions to solve the production quality problems of the target mining lamp in the production process, thereby ensuring the product quality of the target mining lamp.

[0148] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0149] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0150] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned quality prediction results, the above-mentioned quality prediction results can also be stored in a blockchain node.

[0151] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0152] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0153] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0155] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0156] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a mining lamp production control device 300 based on deep learning. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0157] An embodiment of the present invention provides a mining lamp production control device 300 based on deep learning. The mining lamp production control device 300 based on deep learning includes:

[0158] The acquisition module 310 is used to collect parameter data in the production environment of the mining lamp based on preset sensors during the production process of the target mining lamp;

[0159] A preprocessing module 320 is used to preprocess the parameter data to obtain corresponding target parameter data;

[0160] A first calling module 330 is used to call a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data;

[0161] A prediction module 340, configured to perform prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp;

[0162] A judgment module 350 is used to judge whether the quality prediction result is of low quality;

[0163] The adjustment module 360 ​​is used to, if yes, perform corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy.

[0164] Optionally, the deep learning-based mining lamp production control device 300 further includes:

[0165] A first acquisition module, used to acquire production parameter data corresponding to the finished miner's lamp, and to acquire historical quality inspection data corresponding to the finished miner's lamp;

[0166] A construction module, used to construct corresponding sample data based on the production parameter data and the historical quality inspection data;

[0167] A partitioning module, used for partitioning the sample data into a training data set and a validation data set;

[0168] A training module, used to train the deep learning model using the training data set to obtain a corresponding first model;

[0169] An evaluation module, configured to perform a performance evaluation on the first model based on the verification data set to obtain a second model that meets preset performance conditions;

[0170] A determination module is used to use the second model as the quality prediction model.

[0171] Optionally, the adjustment module 360 ​​includes:

[0172] A first acquisition submodule, used to obtain the correlation result between each of the parameter data and the quality prediction result;

[0173] A screening submodule, used for screening out key parameters from all the parameter data based on the correlation results;

[0174] A second acquisition submodule is used to acquire a specified parameter adjustment strategy corresponding to the key parameter;

[0175] The adjustment submodule is used to perform corresponding adjustment processing on the key parameters based on the specified parameter adjustment strategy.

[0176] Optionally, the first acquisition submodule includes:

[0177] An acquisition unit, used for acquiring a plurality of preset statistical algorithms;

[0178] A screening unit, used for screening out a target statistical algorithm from all the statistical algorithms;

[0179] A calculation unit, used for calculating the correlation score between the specified parameter data and the quality prediction result based on the target statistical algorithm; wherein the specified parameter data is any one parameter among all the parameter data;

[0180] A determination unit is used to use the correlation score as a specified correlation result between the specified parameter data and the quality prediction result.

[0181] Optionally, the preprocessing module 320 includes:

[0182] A first processing submodule, used for performing data cleaning processing on the parameter data to obtain corresponding first parameter data;

[0183] A second processing submodule, used for performing data normalization processing on the first parameter data to obtain corresponding second parameter data;

[0184] A third processing submodule, used for performing format conversion processing on the second parameter data to obtain corresponding third parameter data;

[0185] A determination submodule is used to use the third parameter data as the target parameter data.

[0186] Optionally, the deep learning-based mining lamp production control device 300 further includes:

[0187] The second calling module is used to call the preset data buffer area;

[0188] A first acquisition module, used to acquire a preset data transmission strategy;

[0189] A storage module is used to store the target parameter data in the data cache area based on the data transmission strategy.

[0190] Optionally, the deep learning-based mining lamp production control device 300 further includes:

[0191] A display module, used to display the quality prediction result on a preset monitoring screen;

[0192] A generation module, used to generate corresponding warning information based on the quality prediction result;

[0193] The second acquisition module is used to obtain the communication information of relevant personnel;

[0194] A sending module is used to send the warning information to the relevant personnel based on the communication information.

[0195] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0196] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0197] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0198] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as the program code of the mining lamp production control method based on deep learning, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0199] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the program code of the deep learning-based mining lamp production control method.

[0200] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0201] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the application crash processing program, and the application crash processing program can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned deep learning-based mining lamp production control method.

[0202] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0203] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0204] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A mining lamp production control method based on deep learning, characterized in that: include: During the production process of the target mining lamp, parameter data in the mining lamp production environment is collected based on preset sensors; Preprocessing the parameter data to obtain corresponding target parameter data; Calling a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data; Performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp; Determining whether the quality prediction result is of low quality; If so, the parameter data is adjusted accordingly based on a preset parameter adjustment strategy.

2. The method according to claim 1, characterized in that Before calling the preset quality prediction model, the method further includes: Acquiring production parameter data corresponding to a finished miner's lamp, and acquiring historical quality inspection data corresponding to the finished miner's lamp; Constructing corresponding sample data based on the production parameter data and the historical quality inspection data; Dividing the sample data into a training data set and a validation data set; Using the training data set to train the deep learning model to obtain a corresponding first model; Performing a performance evaluation on the first model based on the validation data set to obtain a second model that meets preset performance conditions; The second model is used as the quality prediction model.

3. The method according to claim 1, characterized in that The corresponding adjustment processing of the parameter data based on the preset parameter adjustment strategy includes: Obtaining correlation results between each of the parameter data and the quality prediction results; Filtering out key parameters from all the parameter data based on the correlation results; Obtaining a specified parameter adjustment strategy corresponding to the key parameter; The key parameters are adjusted accordingly based on the specified parameter adjustment strategy.

4. The method according to claim 3, characterized in that The obtaining of the correlation results between each of the parameter data and the quality prediction result includes: Get multiple preset statistical algorithms; Selecting a target statistical algorithm from all the statistical algorithms; Calculating a correlation score between the specified parameter data and the quality prediction result based on the target statistical algorithm; wherein the specified parameter data is any one parameter among all the parameter data; The correlation score is used as a specified correlation result between the specified parameter data and the quality prediction result.

5. The method according to claim 1, characterized in that The preprocessing of the parameter data to obtain corresponding target parameter data includes: Performing data cleaning processing on the parameter data to obtain corresponding first parameter data; Performing data normalization processing on the first parameter data to obtain corresponding second parameter data; Performing format conversion processing on the second parameter data to obtain corresponding third parameter data; The third parameter data is used as the target parameter data.

6. The method according to claim 1, characterized in that After preprocessing the parameter data to obtain corresponding target parameter data, the method further includes: Call the preset data buffer; Obtaining a preset data transmission strategy; Based on the data transmission strategy, the target parameter data is stored in the data buffer area.

7. The method according to claim 1, characterized in that After the parameter data is adjusted accordingly based on the preset parameter adjustment strategy, the method further includes: Displaying the quality prediction result on a preset monitoring screen; Generate corresponding warning information based on the quality prediction result; Obtain communication information of relevant personnel; Based on the communication information, the warning information is sent to the relevant personnel.

8. A mining lamp production control device based on deep learning, characterized in that: include: The acquisition module is used to collect parameter data in the production environment of the mining lamp based on preset sensors during the production process of the target mining lamp; A preprocessing module, used for preprocessing the parameter data to obtain corresponding target parameter data; A first calling module is used to call a preset quality prediction model; wherein the quality prediction model is a model generated by training a preset deep learning model based on pre-constructed sample data; A prediction module, used for performing prediction processing on the target parameter data based on the quality prediction model to obtain a quality prediction result corresponding to the target mining lamp; A judgment module, used to judge whether the quality prediction result is of low quality; The adjustment module is used to, if yes, perform corresponding adjustment processing on the parameter data based on a preset parameter adjustment strategy.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the mining lamp production control method based on deep learning as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the deep learning-based mining lamp production control method as described in any one of claims 1 to 7.

Images