Method and device for adjusting production mode and electronic equipment

Abstract

The invention discloses a method and device for adjusting a production mode and electronic equipment. The method comprises the steps that detection data of a to-be-detected area in a target statistical period is acquired, the to-be-detected area is an area where production activities exist, and the detection data at least comprise the environment temperature, the environment humidity and the electricity consumption of the to-be-detected area; a production mode prediction model is adopted to process and analyze the detection data, a prediction result is obtained, the prediction result is used for determining a production mode currently adopted by the to-be-detected area, and the production mode comprises high-temperature production halt and high-temperature production; and adjusting the production mode of the to-be-detected area according to the prediction result. The technical problems that the abrasion of production equipment is increased and the production efficiency is reduced due to the lack of a scheme for detecting whether the high-temperature production stop is executed in a region are solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for adjusting a production mode, and an electronic device. Background Art

[0002] With the change of global climate, high temperature weather is becoming more and more frequent, which has a significant impact on production activities. Continuous high temperature environment may not only cause overheating, performance degradation or even damage of production equipment, but also affect the work efficiency of staff; therefore, high temperature shutdown conditions are set for areas with different production conditions. High temperature shutdown means that when the equipment temperature or ambient temperature exceeds the corresponding preset temperature value, the production activities in the area are stopped. However, in actual operation, there is a lack of solutions to detect whether a region has implemented high temperature shutdown; there is a problem that it is impossible to ensure that production activities are stopped in time when the conditions for high temperature shutdown are met in the area, resulting in increased wear and tear of production equipment and reduced production efficiency.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for adjusting the production mode, and an electronic device to at least solve the technical problem of increased wear on production equipment and reduced production efficiency due to the lack of a solution to detect whether a high-temperature shutdown is executed in an area.

[0005] According to one aspect of an embodiment of the present application, a method for adjusting a production mode is provided, comprising: obtaining detection data of an area to be detected in a target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data includes at least: ambient temperature, ambient humidity, and electricity consumption of the area to be detected; using a production mode prediction model to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training a machine learning model using historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; adjusting the production mode of the area to be detected according to the prediction result.

[0006] Optionally, a production mode prediction model is used to process and analyze the detection data, including: for each type of detection data, determining the average value of the detection data, and determining the standard deviation of the detection data, and determining the characteristic vector corresponding to the detection data based on the average value and the standard deviation; determining the weight coefficient corresponding to each type of detection data, and determining the input data based on the characteristic vector and the weight coefficient, wherein the weight coefficient is used to indicate the correlation between the detection data and the production mode, and the weight coefficient is determined based on historical production information; and using the production mode prediction model to process and analyze the input data to obtain a prediction result.

[0007] Optionally, the historical detection data include: historical ambient temperature, historical ambient humidity, historical electricity consumption; the weight coefficient is determined by the following method: respectively determine the average value of the historical ambient temperature, the average value of the historical ambient humidity, the average value of the historical electricity consumption, and the frequency of high-temperature shutdown in the historical production mode; determine the first weight coefficient corresponding to the ambient temperature according to the historical ambient temperature, the average value of the historical ambient temperature, the historical production mode and the frequency; determine the second weight coefficient corresponding to the ambient humidity according to the historical ambient humidity, the average value of the historical ambient humidity, the historical production mode and the frequency; determine the third weight coefficient corresponding to the electricity consumption according to the historical electricity consumption, the average value of the historical electricity consumption, the historical production mode and the frequency.

[0008] Optionally, input data is determined based on the feature vector and the weight coefficient, including: determining a target weight coefficient greater than a preset value among multiple weight coefficients, wherein the preset value is used to indicate the lowest correlation between the detection data and the production mode; determining the target detection data corresponding to the target weight coefficient, and determining the target feature vector corresponding to the target detection data, and determining a matrix with multiple target feature vectors as elements as a first matrix; determining the product of the elements located at the same position in the first matrix and the second matrix, and determining a matrix with multiple products as elements as a third matrix, wherein the third matrix is ​​the input data, the position is determined by the row number and the column number, and the second matrix is ​​a matrix with multiple target weight coefficients as elements.

[0009] Optionally, a production pattern prediction model is used to process and analyze the input data to obtain a prediction result, including: mapping the input data into a high-dimensional feature vector, wherein the dimension of the high-dimensional feature vector is greater than the dimension of the input data, and the high-dimensional feature vector includes the similarity between the input data and historical production information; determining the prediction result based on the high-dimensional feature vector and a correction parameter, wherein the correction parameter is used to adjust the result obtained by processing the high-dimensional feature vector, and the correction parameter is determined during the training process of the production pattern prediction model.

[0010] Optionally, the correction parameters are obtained by the following method: clustering historical production information into multiple data sets, wherein each data set corresponds to a historical moment, and each data set also includes: historical ambient temperature of the area to be detected, historical ambient humidity of the area to be detected, historical electricity consumption of the area to be detected, and historical production pattern of the area to be detected; for each data set, generating a historical feature vector based on the historical ambient temperature, historical ambient humidity, and historical electricity consumption; using a machine learning model to process and analyze the historical feature vectors to obtain a predicted production pattern; determining independent correction parameters corresponding to the data set based on the historical production pattern contained in the data set and the predicted production pattern corresponding to the data set; and determining the average value of multiple independent correction parameters as the correction parameter.

[0011] Optionally, adjusting the production mode of the area to be detected according to the prediction result includes: comparing the prediction result with a preset threshold to obtain a comparison result, wherein the preset threshold is a critical value for adjusting the production mode of the area to be detected to high-temperature shutdown; when the comparison result indicates that the prediction result is greater than the preset threshold, outputting a first type of indication information, wherein the first type of indication information is used to indicate that there is no need to adjust the production mode of the area to be detected; when the comparison result indicates that the prediction result is less than or equal to the preset threshold, outputting a second type of indication information, wherein the second type of indication information is used to indicate that the production mode of the area to be detected is adjusted to high-temperature shutdown.

[0012] According to another aspect of an embodiment of the present application, a device for adjusting a production mode is also provided, including: an acquisition module, used to acquire detection data of an area to be detected in a target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data includes at least: ambient temperature, ambient humidity, and power consumption of the area to be detected; a processing module, used to process and analyze the detection data using a production mode prediction model to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training a machine learning model using historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; an adjustment module, used to adjust the production mode of the area to be detected according to the prediction result.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a computer program is stored, wherein the method for adjusting the production mode is executed by running the computer program on a device where the non-volatile storage medium is located.

[0014] According to another aspect of an embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned method for adjusting the production mode through the computer program.

[0015] According to another aspect of an embodiment of the present application, a computer program product is also provided, including computer instructions, which implement the steps of the above-mentioned method for adjusting the production mode when executed by a processor.

[0016] In an embodiment of the present application, detection data of a to-be-detected area in a target statistical period is obtained, wherein the to-be-detected area is an area where production activities exist, and the detection data includes at least: ambient temperature, ambient humidity, and power consumption of the to-be-detected area; a production mode prediction model is used to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the to-be-detected area, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training a machine learning model using historical production information of the to-be-detected area as training data, and the historical production information includes: historical detection data and historical production modes; a method for adjusting the production mode of the to-be-detected area according to the prediction result is used. The method combines big data and Internet of Things technologies, obtains data related to production activities in the area (i.e., data to be detected) through real-time detection of areas with production activities, and further determines whether the area complies with the rules of high-temperature shutdown by analyzing the obtained data (i.e., data to be detected). The purpose of automatically detecting the operating environment and production mode of areas with production activities is achieved. If the area currently does not comply with the rules of high-temperature shutdown, the production mode of the area is adjusted in time, thereby achieving the technical effect of timely adjusting the production mode of areas with production activities, thereby solving the technical problem of increased wear of production equipment and reduced production efficiency due to the lack of a solution to detect whether the area implements high-temperature shutdown. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a method for adjusting a production mode according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of steps of a method for adjusting a production mode according to an embodiment of the present application;

[0020] Figure 3 is a structural diagram of a device for adjusting a production mode according to an embodiment of the present application;

[0021] Figure 4 This is a workflow diagram of a device for adjusting a production mode according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] 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 drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In the related art, there is a lack of automated detection of whether the production activity area complies with the high-temperature shutdown rules for production, and it is impossible to ensure that the production activities are stopped in time when the area reaches the high-temperature shutdown conditions, resulting in the production equipment continuing to carry out production activities in a high-temperature environment, increasing the wear of the production equipment and reducing production efficiency. In order to solve this problem, the embodiments of the present application provide relevant solutions, which are described in detail below.

[0025] According to an embodiment of the present application, a method embodiment for adjusting a production mode is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for adjusting a production mode. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for adjusting the production mode in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned method for adjusting the production mode is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0031] The embodiment of the present application provides a method for adjusting the production mode in the above operating environment. Figure 2 is a flowchart of the steps of the method for adjusting the production mode provided in an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0032] Step S202, obtaining detection data of the area to be detected in the target statistical period, wherein the area to be detected is an area where production activities occur, and the detection data at least includes: ambient temperature, ambient humidity, and power consumption of the area to be detected.

[0033] An embodiment of the present application provides a solution for timely detecting whether the area with production activities complies with the high-temperature production shutdown rule by detecting production activity-related data in the area with production activities (i.e., the area to be detected), and timely adjusting the production mode of the area. The area to be detected can be any area with production activities, such as a production line, a computer room, a warehouse, etc. The detection period (i.e., the target statistical period) can be a period of time. For example, if real-time detection is required, the detection period (i.e., the target statistical period) can be set to the period of time "from 10 minutes (or two minutes, or 30 seconds) before the current moment to the current moment". In step S202, data (i.e., detection data) related to production activities in the area to be detected during the detection period (i.e., the target statistical period) are obtained. The method provided in the embodiment of the present application is used to determine the current environmental state of the detection area, as well as the production mode of the area to be detected under the current environment. Therefore, the acquired detection data include: the following data related to the environmental state of the area to be detected: the ambient temperature (tem) and ambient humidity (hum) of the area to be detected; the following data related to the production mode of the area to be detected: the electricity consumption (elc) generated by the area to be detected in the target statistical period; the above-mentioned ambient temperature (tem) and ambient humidity (hum) can be obtained by deploying sensors in the area to be detected.

[0034] Step S204, use the production mode prediction model to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown, high-temperature production, and the production mode prediction model is obtained by training the machine learning model with the historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes.

[0035] The method provided in the embodiment of the present application combines the technology of big data to process and analyze the data of the area to be detected. Specifically, a machine learning model is introduced to execute big data related technologies; therefore, in step S204, a production mode prediction model is used to process and analyze the data to be detected obtained in step S202 to obtain an evaluation factor (i.e., a prediction result) for determining the production mode adopted by the area to be detected at the current moment. In this embodiment, the production mode of the area to be detected is divided into the following two categories: one is that when the environmental state of the area to be detected has reached a preset shutdown temperature, the area to be detected stops production (i.e., high-temperature shutdown); the other is that when the environmental state of the area to be detected has reached a preset shutdown temperature, the area to be detected continues production (i.e., high-temperature production). The production mode prediction model used in step S202 is generated by training a machine learning model with classification and regression analysis functions, for example, it can be generated by training a support vector machine (SVM), a decision tree, a random forest, etc.; when training the above-mentioned machine learning model with classification and regression analysis functions, the historical production information of the area to be detected is used as training data, wherein the historical production information includes not only the environmental data and production equipment data obtained from the detection of the area to be detected at historical moments, but also the actual production mode of the area to be detected at historical moments (i.e., the historical production mode).

[0036] It should be noted that before using the production mode prediction model to determine the production mode to be adopted by the to-be-detected area, the method provided in the embodiment of the present application first determines the current production mode of the to-be-detected area according to the power consumption of the to-be-detected area in the detection period (i.e., the target statistical period); specifically, the power consumption threshold value elc is preset. th , power consumption threshold elc th It is the maximum power consumption generated during the target statistical period when the equipment in the detected area is in sleep state. If the power consumption generated in the target statistical period is less than the power consumption threshold elc th, it is determined that the current production mode of the area to be detected is high temperature shutdown; otherwise, if the power consumption generated by the area to be detected in the target statistical period is greater than or equal to the power consumption threshold elc th , the production mode prediction model is further used for analysis.

[0037] In step S204, the production mode prediction model may be loaded into the memory, for example, the raw data of the production mode prediction model may be loaded from the non-volatile memory into the volatile memory, so that the processor runs the production mode prediction model. The raw data of the production mode prediction model refers to unprocessed data, and generally includes parameters and structural data of the production mode prediction model. The structural data may be a calculation relationship based on the parameters, such as a forward propagation calculation relationship between intermediate layers and neurons. Specifically, the structural data may include code related to the structure of the production mode prediction model, such as code for performing related calculations between intermediate layers and neurons.

[0038] In one embodiment, an area for loading the production mode prediction model can be divided in the memory, which can include a structure data storage area and a parameter storage area. The structure data storage area is used to store structure-related codes, and the parameters referenced by it can point to the address of specific parameters in the parameter storage area through a pointer. During the training process of the production mode prediction model, it may be necessary to update the parameters frequently, and the parameter values ​​in the parameter storage area can be updated.

[0039] Optionally, a production mode prediction model is used to process and analyze the detection data, including: for each type of detection data, determining the average value of the detection data, and determining the standard deviation of the detection data, and determining the characteristic vector corresponding to the detection data based on the average value and the standard deviation; determining the weight coefficient corresponding to each type of detection data, and determining the input data based on the characteristic vector and the weight coefficient, wherein the weight coefficient is used to indicate the correlation between the detection data and the production mode, and the weight coefficient is determined based on historical production information; and using the production mode prediction model to process and analyze the input data to obtain a prediction result.

[0040] In this embodiment, the production mode prediction model is integrated in the equipment / device. In order to use the production mode prediction model to process and analyze the detection data to obtain the evaluation factor (i.e., the prediction result) used to determine the production mode adopted by the detection area at the current moment, after the detection data is initially acquired, the equipment / device in which the production mode prediction model is integrated pre-processes the detection data to obtain the input data of the production mode prediction model, and then uses the production mode prediction model to further process and analyze the input data to finally obtain the evaluation factor (i.e., the prediction result). The above-mentioned method of pre-processing the detection data and generating input data includes the following three steps: characteristic vector calculation, weight coefficient determination, and input data formation; wherein, in the step of characteristic quantity calculation, the average value and standard deviation are calculated for each type of detection data (ambient temperature, ambient humidity, power consumption) to form a standardized characteristic vector. The characteristic vector of each type of detection data is used to describe the current environmental state. The above-mentioned step of generating characteristic quantity calculation can be expressed as the following formula: Among them, x represents the original data (i.e., the detection data), μ is the average value of the original data, σ is the standard deviation of the original data, and X ′ is the feature vector corresponding to the original data; when determining the feature vector of ambient temperature, x is a plurality of ambient temperatures in the target statistical period; when determining the feature vector of ambient humidity, x is a plurality of ambient humidity in the target statistical period; when determining the feature vector of power consumption, x is a plurality of power consumption in the target statistical period. Next, determine the weight coefficient corresponding to each type of detection data, wherein the weight coefficient is determined by the correlation between each type of detection data and the production mode determined based on historical production information, and the weight coefficient corresponding to each type of detection data is used to indicate the correlation between this type of detection data and the production mode of the area to be detected, and the larger the weight coefficient, the higher the correlation. In the step of forming the input data, the feature vector and the weight coefficient are weightedly combined to obtain the input data for processing and analysis by the production mode prediction model.

[0041] According to some optional embodiments of the present application, the historical detection data include: historical ambient temperature, historical ambient humidity, historical electricity consumption; the weight coefficient is determined by the following method: respectively determine the average value of the historical ambient temperature, the average value of the historical ambient humidity, the average value of the historical electricity consumption, and the frequency of high-temperature shutdown in the historical production mode; determine the first weight coefficient corresponding to the ambient temperature according to the historical ambient temperature, the average value of the historical ambient temperature, the historical production mode and the frequency; determine the second weight coefficient corresponding to the ambient humidity according to the historical ambient humidity, the average value of the historical ambient humidity, the historical production mode and the frequency; determine the third weight coefficient corresponding to the electricity consumption according to the historical electricity consumption, the average value of the historical electricity consumption, the historical production mode and the frequency.

[0042] As mentioned in the above embodiment, the weight coefficient is determined by the correlation between each type of detection data and the production mode determined based on the historical production information, wherein, as mentioned in step S204, the historical production information includes the environmental data and production equipment data obtained by detecting the area to be detected at the historical moment, and also includes the actual production mode (i.e., historical production mode) of the area to be detected at the historical moment, wherein the environmental data obtained by detecting the area to be detected at the historical moment includes: the historical ambient temperature and historical ambient humidity of the area to be detected. In this embodiment, the weight coefficient is calculated based on the Pearson correlation coefficient, and the weight coefficient of each type of detection data is determined according to its corresponding historical detection data (historical ambient temperature, or historical ambient humidity, or historical electricity consumption) and the frequency of occurrence of the high temperature shutdown mode in the historical production mode. The method for determining the weight coefficient can be expressed by the following formula: Where b represents the type of test data (temperature, humidity, or environmental parameters), Y represents the production mode of high temperature shutdown, and b i represents the historical detection data at the i-th historical detection moment, Represents the average value of historical detection data, y i represents the frequency of high-temperature shutdown in the production mode of the area to be detected at the i-th historical detection moment, Represents the average frequency of multiple high-temperature shutdowns; if the weight coefficient of the ambient temperature is calculated, b i represents the ambient temperature at the i-th historical detection moment, ρ b,Y represents the weight coefficient of ambient temperature (i.e., the first weight coefficient); if the weight coefficient of ambient humidity is calculated, b i represents the ambient humidity at the i-th historical detection moment, ρ b,Y represents the weight coefficient of ambient humidity (i.e., the second weight coefficient); if it is the weight coefficient for calculating power consumption, b i represents the power consumption at the i-th historical detection moment, ρ b,Y The weight coefficient representing the power consumption (ie, the third weight coefficient).

[0043] According to some other optional embodiments of the present application, input data is determined based on feature vectors and weight coefficients, including: determining a target weight coefficient greater than a preset value among multiple weight coefficients, wherein the preset value is used to indicate the lowest correlation between the detection data and the production mode; determining the target detection data corresponding to the target weight coefficient, and determining the target feature vector corresponding to the target detection data, and determining a matrix with multiple target feature vectors as elements as a first matrix; determining the product of the first matrix and the elements located at the same position in the second matrix, and determining a matrix with multiple products as elements as a third matrix, wherein the third matrix is ​​input data, the position is determined by the row number and the column number, and the second matrix is ​​a matrix with multiple target weight coefficients as elements.

[0044] In the embodiment of the present application, each time the production mode prediction model is used to predict the current production mode of the area to be detected, the detection data obtained in step S202 is screened according to the weight coefficient corresponding to each type of detection data, and multiple types of detection data (i.e., target detection data) with high correlation are screened according to the weight coefficient to generate input data for the production mode prediction model; specifically, the weight coefficient representing the lowest correlation (i.e., the preset value) is used as the screening criterion, and the type of detection data corresponding to the weight coefficient greater than the preset value (i.e., the target weight coefficient) is used as the target detection data for generating input data, wherein the preset value can be set to 0.2. The process of generating input data can be expressed as the following formula: γ = B x *X, where X is a matrix consisting of multiple weight coefficients (i.e., the second matrix), B x is a matrix (i.e., the first matrix) composed of eigenvectors (i.e., target eigenvectors) corresponding to multiple target detection data, γ is the final input data, expressed in the form of a matrix (i.e., the third matrix); through the processing rules defined by the above formula, the matrix B with the eigenvectors (i.e., target eigenvectors) corresponding to the target detection data as elements is x (i.e., the first matrix) and the matrix X (i.e., the second matrix) with the weight coefficients of the target detection data as elements are processed by Hadamard product to obtain input data, wherein the input data can be expressed in the form of a matrix (i.e., the third matrix). Wherein, when performing the Hadamard product on the first matrix and the second matrix, only the two elements with the same position in the first matrix and the second matrix are correspondingly multiplied, and the result of the multiplication is used as the element at that position in the third matrix. The position of each of the above elements is jointly determined by the row number and column number of the element. For example, if element A is in the 3rd row and 5th column of the first matrix, the position of element A is (3, 5); when performing the Hadamard product on the first matrix and the second matrix, the element B in the 3rd row and 5th column of the second matrix is ​​multiplied by the element A, and the result "A*B" is used as the element of the 3rd row and 5th column of the third matrix γ.

[0045] According to some optional embodiments of the present application, a production mode prediction model is used to process and analyze input data to obtain prediction results, including: mapping the input data into a high-dimensional feature vector, wherein the dimension of the high-dimensional feature vector is greater than the dimension of the input data, and the high-dimensional feature vector includes the similarity between the input data and historical production information; determining the prediction result based on the high-dimensional feature vector and correction parameters, wherein the correction parameters are used to adjust the result obtained by processing the high-dimensional feature vector, and the correction parameters are determined during the training process of the production mode prediction model.

[0046] In this embodiment, the process of processing and analyzing the input data by the production mode prediction model is divided into two parts: high-dimensional feature mapping and prediction result generation. In order to enrich the correlation between the input data (for example, the similarity between the input data and the historical production information), the production mode prediction model first maps the input data to a higher dimensional vector (i.e., a high-dimensional feature vector), further processes and analyzes the high-dimensional feature vector in combination with the correction parameters, and outputs the final prediction result. In an embodiment of the present application, the production mode prediction model uses a kernel function to map the input data to a higher dimensional vector (i.e., a high-dimensional feature vector). In this embodiment, a radial basis kernel function is selected as the kernel function for mapping the input data to a higher dimensional vector (i.e., a high-dimensional feature vector), wherein the process of mapping the input data to a high-dimensional feature vector can be expressed as a formula: K(X,X i ) represents the high-dimensional feature vector output after kernel function mapping, X j Represents the detection data in the target statistical period, such as X i Represents historical test data (historical ambient temperature, or historical ambient humidity), such as X i Represents any historical detection data, X j represents any one of the multiple detection data obtained in the target statistical period, g is a preset value, representing the kernel function base width, which determines the sample data X j and X i The decay rate of the similarity is used to improve the nonlinear classification ability of the production mode prediction model and improve the accuracy of the prediction results; after the processing shown in the above formula, the input data can be mapped to a high-dimensional feature vector. Furthermore, the correction parameters determined in the model training process and the high-dimensional feature vector generated by the mapping are combined to determine the evaluation factor (i.e., the prediction result). The process of generating the prediction result can be expressed as the following formula: Among them, f(x) represents the output evaluation factor (i.e., the prediction result), K(X j ,X i ) is a high-dimensional feature vector generated by mapping the input data.

[0047] a i and is a set of Lagrange multipliers corresponding to sample data i, which is determined during the training process of the production mode prediction model. i Represents the Lagrangian operator corresponding to the i-th sample data (the i-th element in the high-dimensional feature vector), represents the optimal Lagrangian operator corresponding to the ith sample data (the ith element in the high-dimensional feature vector), b represents the correction parameter, and its specific value is determined during the training process of the production pattern prediction model, and n represents the total number of sample data (that is, the number of elements in the high-dimensional feature vector).

[0048] Optionally, the correction parameters are obtained by the following method: clustering historical production information into multiple data sets, wherein each data set corresponds to a historical moment, and each data set also includes: historical ambient temperature of the area to be detected, historical ambient humidity of the area to be detected, historical electricity consumption of the area to be detected, and historical production pattern of the area to be detected; for each data set, generating a historical feature vector based on the historical ambient temperature, historical ambient humidity, and historical electricity consumption; using a machine learning model to process and analyze the historical feature vectors to obtain a predicted production pattern; determining independent correction parameters corresponding to the data set based on the historical production pattern contained in the data set and the predicted production pattern corresponding to the data set; and determining the average value of multiple independent correction parameters as the correction parameter.

[0049] As mentioned in the previous embodiment, the correction parameter used by the production mode prediction model to determine the prediction result is determined in the process of training the production mode prediction model using the historical production information of the area to be detected. Specifically, in this embodiment, the process of determining the correction parameter (b) can be expressed as the following formula:

[0050]

[0051] Among them, ξ is the relaxation coefficient, C is the penalty coefficient, and their values ​​are all pre-set. When determining the correction parameter (b), whether to use the above formula ① or formula ② is determined according to the error between the prediction result output by the model for the historical detection data (historical ambient temperature, historical ambient humidity and historical electricity consumption) in the training sample and the frequency of high-temperature shutdown in the historical production mode in the training sample; when the difference between the prediction result output for the historical detection data and the frequency of high-temperature shutdown in the historical production mode is greater than the sum of the frequency of high-temperature shutdown and ξ, this round of iterative training uses formula ① to determine the correction parameter of this round (i.e., independent correction parameter); otherwise, when the difference between the prediction result output for the historical detection data and the frequency of high-temperature shutdown in the historical production mode is less than or equal to the sum of the frequency of high-temperature shutdown and ξ, this round of iterative training uses formula ② to determine the correction parameter of this round (i.e., independent correction parameter). Finally, the average value of multiple independent correction parameters determined in multiple rounds of iterations is determined as the correction parameter (b) used when applying the production mode prediction model. The processing process of the training samples in the training process is similar to the process of data processing and analysis in the application process. Both need to generate high-dimensional feature vectors first and then generate prediction results. Since the data contained in the training samples are generated in the area to be detected at multiple historical moments, during the training process, the historical production information (historical environmental temperature, humidity, power consumption and production mode) is first clustered into multiple data sets according to the corresponding historical moments. The above historical moments can be determined by the detection moments corresponding to the historical production modes. The historical environmental temperature, humidity, power consumption and production modes at the same historical detection moment are classified into one data set to obtain multiple data sets. For each data set, the machine learning model in training generates a corresponding high-dimensional feature vector (i.e., historical feature vector) based on the historical detection data in the data set, and then processes the historical feature vector to output the prediction result (i.e., predicted production mode); in this embodiment, the predicted production mode is expressed in the form of probability, and the output prediction mode is two probability values, one is the probability of high-temperature shutdown, and the other is the probability of high-temperature production.

[0052] Step S206, adjusting the production mode of the area to be inspected according to the prediction result.

[0053] In step S206, the production mode of the area to be inspected is adjusted according to the evaluation factor output by the production mode prediction model. In the embodiment of the present application, the prediction result output in step S204 is actually an evaluation factor for evaluating whether the area to be inspected should be operated in a high-temperature shutdown mode. In step S206, by determining whether the current actual production mode of the area to be inspected is the same as the production mode indicated by the evaluation factor, the production mode of the area to be inspected is further adjusted to ensure that the current production mode of the area to be inspected is consistent with the production mode indicated by the evaluation factor.

[0054] Optionally, adjusting the production mode of the area to be detected according to the prediction result includes: comparing the prediction result with a preset threshold to obtain a comparison result, wherein the preset threshold is a critical value for adjusting the production mode of the area to be detected to high-temperature shutdown; when the comparison result indicates that the prediction result is greater than the preset threshold, outputting a first type of indication information, wherein the first type of indication information is used to indicate that there is no need to adjust the production mode of the area to be detected; when the comparison result indicates that the prediction result is less than or equal to the preset threshold, outputting a second type of indication information, wherein the second type of indication information is used to indicate that the production mode of the area to be detected is adjusted to high-temperature shutdown.

[0055] As mentioned in the previous embodiment, the prediction result output by step S204 is an evaluation factor for evaluating whether the area to be detected should be operated in a high-temperature shutdown mode. The evaluation factor is output in the form of a probability value to the next module of the device / equipment where the production mode prediction model is located. When the next module determines the production mode that the area to be detected should currently adopt based on the evaluation factor, the evaluation factor (i.e., the prediction result) is compared with the preset threshold value, wherein the preset threshold value is set as the trigger point of the high-temperature shutdown of the area to be detected in the actual production operation, which is the critical value (cva) at which the production mode of the area to be detected is adjusted to the high-temperature shutdown. th ), determine the adjustment method of the area to be detected according to the comparison results. Specifically, the evaluation factor (i.e., the prediction result) is greater than the critical value (cva th ), then the first type of indication information (such as "continue production") is output, indicating that the current production mode does not need to be adjusted; if the prediction result is lower than or equal to the critical value, the second type of indication information (such as "high temperature stop production") is output, indicating that the production mode is immediately adjusted to high temperature stop production to ensure safety. In addition, if the area to be detected is a production activity carried out by humans, the second type of indication information output can be a text message and / or voice message for notifying the cessation of production.

[0056] Through the above steps, real-time detection of the production situation of the area to be detected can be achieved, and the production mode can be automatically adjusted according to the production situation of the area to be detected, effectively avoiding production safety accidents and improving production efficiency. At the same time, through intelligent and automated methods, the frequency and intensity of manual intervention are reduced, the efficiency and effectiveness of production management are improved, and safety protection and efficiency improvement are provided for various production activities.

[0057] Figure 3 is a structural diagram of a device for adjusting a production mode provided in an embodiment of the present application, such as Figure 3As shown, the device for adjusting the production mode includes: an acquisition module 30, which is used to obtain the detection data of the area to be detected in the target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data at least includes: the ambient temperature, ambient humidity, and power consumption of the area to be detected; a processing module 32, which is used to use a production mode prediction model to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training the machine learning model with the historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; an adjustment module 34, which is used to adjust the production mode of the area to be detected according to the prediction result.

[0058] Figure 4 It is a workflow diagram of the device for adjusting the production mode, such as Figure 4 As shown, when the device is used to execute the method provided in the embodiment of the present application, the acquisition module 30 acquires the temperature data tem and humidity data hum of the to-be-detected area in the detection period (i.e., the target statistical period) from the multiple types of sensors in the to-be-detected area, and acquires the power consumption elc generated by the to-be-detected area in the detection period from the equipment control system of the to-be-detected area. The acquisition module 30 combines the above detection data into a data set (A rt ), A rt ={tem, hum, elc} is transmitted to the processing module 32, and the processing module 32 uses the production mode prediction model therein to process the data set (A rt ) is processed and analyzed, and an evaluation factor for determining the production mode that should be currently adopted in the area to be detected is output; the processing module 32 uses the production mode prediction model to process the data set (A rt ) is processed and analyzed before the data in the preprocessing is annotated (i.e., the feature vector calculation, weight coefficient determination and input data formation included in the preprocessing) to generate input data, and then the production mode prediction model is used to process and analyze the input data, and the evaluation factor y (i.e., the prediction result) is output to the adjustment module 34; when determining the weight coefficient, the Pearson coefficient of each type of detection data is calculated as the weight coefficient; when forming the input data, the Hadamard product algorithm is used to fuse the weight coefficient with the acquired detection data to obtain the fusion factor r (i.e., the input data). As mentioned in the above embodiment, the production mode prediction model can be expressed as the following formula in the process of processing and analyzing the detection data: In addition, the processing module 32 uses the production mode prediction model to process the data set (A rt ) before processing and analyzing the data, it will first pass the preset power consumption threshold elc th and data set (A rt) determines whether the area to be detected is currently in a high-temperature shutdown mode. If elc is less than elc th , it is determined that the current production mode of the area to be detected is high temperature shutdown, and the processing module no longer enables the processing module 32; otherwise, if elc is greater than or equal to elc th , the production mode prediction model is further used for analysis, and the evaluation factor y is output to the adjustment module 34. The adjustment module 34 uses the preset high-temperature shutdown critical value cva (i.e., the preset value) to compare with the evaluation factor y, and determines the adjustment method of the area to be detected according to the comparison result. Specifically, if the evaluation factor (i.e., the prediction result) is greater than the critical value (cva), the first type of indication information (such as "continue production") is output, indicating that the current production mode does not need to be adjusted; if the prediction result is lower than or equal to the critical value, the second type of indication information (such as "high-temperature shutdown") is output, indicating that the production mode is immediately adjusted to high-temperature shutdown to ensure safety.

[0059] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0060] An embodiment of the present application further provides a non-volatile storage medium, in which a computer program is stored, wherein the above method for adjusting the production mode is executed by running the computer program on a device where the non-volatile storage medium is located.

[0061] The above-mentioned non-volatile storage medium is used to store programs that perform the following functions: obtaining detection data of the area to be detected in the target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data at least includes: the ambient temperature, ambient humidity, and power consumption of the area to be detected; using a production mode prediction model to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training the machine learning model using the historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; adjusting the production mode of the area to be detected according to the prediction result.

[0062] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above method for adjusting the production mode through the computer program.

[0063] The processor in the above-mentioned electronic device is used to run a program that performs the following functions: obtaining detection data of the area to be detected in the target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data includes at least: the ambient temperature, ambient humidity, and power consumption of the area to be detected; using a production mode prediction model to process and analyze the detection data to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production modes include: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training the machine learning model using the historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; adjusting the production mode of the area to be detected according to the prediction result.

[0064] The embodiment of the present application also provides a computer program product, including computer instructions, which implement the steps of the above method for adjusting the production mode when executed by a processor.

[0065] It should be noted that the various modules in the above-mentioned device for adjusting the production mode can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0066] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0067] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0068] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0069] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0070] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0071] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0072] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adjusting a production mode, characterized in that: include: Acquire detection data of the area to be detected in a target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data at least includes: ambient temperature, ambient humidity, and power consumption of the area to be detected; The detection data is processed and analyzed using a production mode prediction model to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production mode includes: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training a machine learning model using historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; The production mode of the area to be inspected is adjusted according to the prediction result.

2. The method according to claim 1, characterized in that: The detection data is processed and analyzed using a production mode prediction model, including: For each type of the detection data, determine the average value of the detection data, determine the standard deviation of the detection data, and determine the feature vector corresponding to the detection data according to the average value and the standard deviation; Determine a weight coefficient corresponding to each type of the detection data, and determine input data according to the feature vector and the weight coefficient, wherein the weight coefficient is used to indicate the relevance of the detection data to the production mode, and the weight coefficient is determined according to the historical production information; The production mode prediction model is used to process and analyze the input data to obtain the prediction result.

3. The method according to claim 2, characterized in that The historical detection data includes: historical ambient temperature, historical ambient humidity, and historical power consumption; The weight coefficient is determined by the following method: Respectively determine the average value of the historical ambient temperature, the average value of the historical ambient humidity, the average value of the historical power consumption, and the frequency of the high-temperature shutdown in the historical production mode; Determining a first weight coefficient corresponding to the ambient temperature according to the historical ambient temperature, the average value of the historical ambient temperature, the historical production mode, and the frequency; Determining a second weight coefficient corresponding to the ambient humidity according to the historical ambient humidity, the average value of the historical ambient humidity, the historical production mode and the frequency; A third weight coefficient corresponding to the power consumption is determined according to the historical power consumption, an average value of the historical power consumption, the historical production mode and the frequency.

4. The method according to claim 2, characterized in that: Determining input data according to the feature vector and the weight coefficient includes: Determining a target weight coefficient greater than a preset value among the plurality of weight coefficients, wherein the preset value is used to indicate a lowest correlation between the detection data and the production mode; Determine target detection data corresponding to the target weight coefficient, determine a target feature vector corresponding to the target detection data, and determine a matrix having a plurality of the target feature vectors as elements as a first matrix; Determine the product of the elements located at the same position in the first matrix and the second matrix, and determine a matrix with multiple of the products as elements as a third matrix, wherein the third matrix is ​​the input data, the position is determined by the row number and the column number, and the second matrix is ​​a matrix with multiple of the target weight coefficients as elements.

5. The method according to claim 2, characterized in that: The input data is processed and analyzed using the production mode prediction model to obtain the prediction result, including: Mapping the input data into a high-dimensional feature vector, wherein the dimension of the high-dimensional feature vector is greater than the dimension of the input data, and the high-dimensional feature vector includes the similarity between the input data and the historical production information; The prediction result is determined according to the high-dimensional feature vector and a correction parameter, wherein the correction parameter is used to adjust the result obtained by processing the high-dimensional feature vector, and the correction parameter is determined during the training process of the production mode prediction model.

6. The method according to claim 5, characterized in that The correction parameters are obtained by the following method: Clustering the historical production information into multiple data sets, wherein each data set corresponds to a historical moment, and each data set simultaneously includes: the historical ambient temperature of the area to be detected, the historical ambient humidity of the area to be detected, the historical power consumption of the area to be detected, and the historical production mode of the area to be detected; For each of the data sets, a historical feature vector is generated according to the historical ambient temperature, the historical ambient humidity and the historical power consumption; the historical feature vector is processed and analyzed using the machine learning model to obtain a predicted production mode; and an independent correction parameter corresponding to the data set is determined according to the historical production mode contained in the data set and the predicted production mode corresponding to the data set; An average value of a plurality of the independent correction parameters is determined as the correction parameter.

7. The method according to claim 1, characterized in that Adjusting the production mode of the area to be inspected according to the prediction result includes: Comparing the prediction result with a preset threshold to obtain a comparison result, wherein the preset threshold is a critical value for adjusting the production mode of the area to be detected to the high-temperature shutdown; When the comparison result indicates that the prediction result is greater than the preset threshold, outputting first type of indication information, wherein the first type of indication information is used to indicate that there is no need to adjust the production mode of the area to be inspected; When the comparison result indicates that the prediction result is less than or equal to the preset threshold, a second type of indication information is output, wherein the second type of indication information is used to indicate that the production mode of the area to be detected is adjusted to the high-temperature shutdown.

8. A device for adjusting a production mode, characterized in that: include: An acquisition module is used to acquire detection data of the area to be detected in a target statistical period, wherein the area to be detected is an area where production activities exist, and the detection data at least includes: ambient temperature, ambient humidity, and power consumption of the area to be detected; A processing module, used for processing and analyzing the detection data by using a production mode prediction model to obtain a prediction result, wherein the prediction result is used to determine the production mode currently adopted by the area to be detected, and the production mode includes: high-temperature shutdown and high-temperature production. The production mode prediction model is obtained by training a machine learning model using historical production information of the area to be detected as training data, and the historical production information includes: historical detection data and historical production modes; An adjustment module is used to adjust the production mode of the area to be detected according to the prediction result.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the method for adjusting the production mode according to any one of claims 1 to 7 is executed by running the computer program on the device where the non-volatile storage medium is located.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method for adjusting the production mode according to any one of claims 1 to 7 through the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for adjusting the production mode described in any one of claims 1 to 7 are implemented.

Images