An industrial computer control method and system based on artificial intelligence

Abstract

The application provides an industrial computer control method and system based on artificial intelligence, wherein the industrial computer control method based on artificial intelligence comprises the following steps: acquiring key heat-emitting component parameters of an industrial computer, and constructing a thermal influence comprehensive index of the industrial computer; establishing a heat dissipation demand prediction model based on the thermal influence comprehensive index of the industrial computer; formulating a heat dissipation control strategy according to a comparison result of the predicted thermal influence comprehensive index and a preset thermal influence comprehensive index safety threshold; and generating a prompt information of cleaning dust of the heat dissipation fan of the industrial computer if the actual thermal influence comprehensive index is greater than the predicted thermal influence comprehensive index after heat dissipation according to the predicted thermal influence comprehensive index after heat dissipation of the heat dissipation control strategy. Through the method and the corresponding system, the wear of the fan motor of the industrial computer can be reduced, the service life of the fan of the industrial computer is increased, and the user can timely find and solve the heat dissipation problem caused by the dust accumulation of the fan.

Description

Technical Field

[0001] The present invention proposes an industrial computer control method and system based on artificial intelligence, and relates to the field of heat dissipation control. Background Art

[0002] Industrial computers (IPCs) are specifically designed for industrial environments. These environments are often characterized by high temperatures, dust, and suboptimal power supplies, and IPCs must operate continuously for extended periods of time. In such environments, excellent heat dissipation design is crucial for ensuring stable operation.

[0003] Traditional IPC cooling control methods use a one-size-fits-all approach to adjust fan speed based on predictions, failing to tailor fan speed to the IPC's own operating conditions. This one-size-fits-all approach, rather than tailoring fan speed to the IPC's own operating conditions, can sometimes increase wear on the fan motor and shorten its lifespan. This is because the motor experiences significant fluctuations in current and mechanical stress during startup, acceleration, and deceleration, making long-term failure more likely. Furthermore, sometimes hardware issues, such as dust accumulation on the cooling fan, can render fan speed adjustments useless. This approach fails to identify any anomalies in the IPC's cooling system based on its own operating status. Summary of the Invention

[0004] The present invention provides an industrial computer control method and system based on artificial intelligence, which predicts heat dissipation requirements and adjusts the predicted heat dissipation cycle. Furthermore, based on the heat dissipation cycle, a cleaning trigger coefficient calculated by a cleaning trigger coefficient model is used to determine whether the industrial computer's own hardware has a heat dissipation failure to solve the above-mentioned problems.

[0005] The present invention proposes an industrial computer control method based on artificial intelligence, the method comprising:

[0006] Obtain parameters of key heat-generating components of industrial computers and construct comprehensive thermal impact indicators for industrial computers;

[0007] Establish a heat dissipation demand prediction model based on the comprehensive thermal impact index of industrial computers;

[0008] Formulate a heat dissipation control strategy based on the comparison results between the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index;

[0009] According to the thermal impact comprehensive index after heat dissipation predicted by the heat dissipation control strategy, if the actual thermal impact comprehensive index is greater than the predicted thermal impact comprehensive index after heat dissipation, a prompt message for cleaning dust from the cooling fan of the industrial computer is generated.

[0010] Furthermore, the parameters of the key heat-generating components of the industrial computer are obtained to construct a comprehensive thermal impact index of the industrial computer, including:

[0011] Obtain parameters of key heat-generating components of the industrial computer, including CPU temperature, GPU temperature, memory chip temperature, heat sink temperature, temperature difference between the two ends of the heat pipe, fan speed, GPU utilization, GPU load, CPU utilization, and CPU load;

[0012] Record the timestamp of each data collection for subsequent time series analysis;

[0013] The thermal impact comprehensive index of the industrial computer is constructed by weighted summing the collected key heating component parameters, and the weight coefficients of the key heating component parameters are determined according to the performance of the industrial computer.

[0014] Furthermore, the weight coefficients of the key heating component parameters are determined according to the performance of the industrial computer, including:

[0015] The process of determining the weight coefficient of the comprehensive thermal impact index is divided into a target layer, a criterion layer, and an indicator layer. The target layer is used to determine the weight coefficient of the comprehensive thermal impact index. The criterion layer includes CPU performance, GPU performance, memory performance, heat sink cooling capacity, heat pipe cooling capacity, internal environment impact, and external environment impact. The indicator layer corresponds to the temperature parameter.

[0016] For industrial control hosts with different performance, the relative importance of each criterion is analyzed, the host performance parameters are quantitatively analyzed, and a judgment matrix is ​​constructed;

[0017] The maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated using the eigenroot method. After normalization, the eigenvector is the weight vector of each criterion relative to the target layer.

[0018] The judgment matrix is ​​tested for consistency, the consistency index is calculated, and the corresponding average random consistency index is found. Then the consistency ratio is calculated. When the consistency ratio is less than 0.1, the judgment matrix is ​​considered to have satisfactory consistency. Otherwise, the judgment matrix needs to be readjusted.

[0019] Furthermore, a heat dissipation demand prediction model is established based on the comprehensive thermal impact indicators of the industrial computer, including:

[0020] Acquire a historical data set, the historical data set including historical key heat-generating component parameters of the industrial computer and corresponding comprehensive thermal impact indicators;

[0021] The historical data set is divided into a training set and a validation set. The training set is put into the neural network model for training until the set model training end conditions are met, and finally a heat dissipation demand prediction model is obtained;

[0022] Calculate the prediction period, and when the time reaches the prediction period, predict the temperature of the industrial computer through the established heat dissipation demand prediction model.

[0023] Furthermore, the prediction period is calculated, including:

[0024] The prediction period is calculated by using a prediction period model. Specifically, the prediction period model is:

[0025] ;

[0026] in, represents the adjusted forecast period, represents the basic forecast period, Indicates the difference in CPU usage between the current moment and the previous moment. Indicates the difference between the GPU usage at the current moment and the previous moment, Indicates the average value of CPU usage during the preset time period. represents the average GPU usage rate in the past preset time period, β represents the first weight coefficient, and σ represents the second weight coefficient.

[0027] Furthermore, a heat dissipation control strategy is formulated based on the comparison result of the predicted comprehensive heat impact index with the preset safety threshold of the comprehensive heat impact index, including:

[0028] Comparing the predicted comprehensive heat dissipation impact index with the preset comprehensive heat impact index;

[0029] If the predicted comprehensive heat dissipation impact index is greater than the preset comprehensive heat impact index, the speed of the heat dissipation fan is adjusted through a control algorithm.

[0030] Furthermore, based on the thermal impact comprehensive index after heat dissipation predicted by the heat dissipation control strategy, if the actual thermal impact comprehensive index is greater than the predicted thermal impact comprehensive index after heat dissipation, a prompt message for cleaning dust from the industrial computer heat dissipation fan is generated, including:

[0031] Obtain the predicted comprehensive index value of thermal impact after heat dissipation;

[0032] Use the temperature sensor installed on the industrial computer to obtain the actual thermal impact comprehensive index value of the current industrial computer after heat dissipation;

[0033] According to the predicted comprehensive index value of heat impact after heat dissipation and the actual comprehensive index value of heat impact after heat dissipation, the cleaning trigger coefficient K is calculated with the help of the cleaning trigger coefficient model. When the cleaning trigger coefficient K is greater than the first preset threshold and When it is greater than zero, a gradient warning signal is generated;

[0034] If the gradient warning signal lasts for three prediction cycles, a fan cleaning prompt message is output to the display of the industrial computer.

[0035] The present invention proposes an industrial computer control system based on artificial intelligence, the system comprising:

[0036] Build a comprehensive thermal impact index module to obtain the parameters of key heat-generating components of industrial computers and build a comprehensive thermal impact index for industrial computers;

[0037] Establish a heat dissipation demand prediction model module, which is used to establish a heat dissipation demand prediction model based on the comprehensive thermal impact indicators of industrial computers;

[0038] The heat dissipation control module is used to formulate a heat dissipation control strategy based on the comparison result of the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index;

[0039] The prompt module is used to generate a prompt message to clean the dust of the industrial computer cooling fan if the actual comprehensive heat impact index is greater than the predicted comprehensive heat impact index after cooling according to the heat dissipation control strategy.

[0040] Furthermore, an artificial intelligence-based industrial computer control system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the artificial intelligence-based industrial computer control method when executing the program.

[0041] The present invention proposes a computer program product, comprising a computer program and / or instructions, characterized in that when the computer program and / or instructions are executed by a processor, the steps of the industrial computer control method based on artificial intelligence are implemented.

[0042] The beneficial effects of the present invention are as follows: the comprehensive thermal impact index comprehensively considers multiple factors such as the various heat-generating components, heat-dissipating components, and internal and external ambient temperatures inside the industrial computer, and can accurately evaluate the heat dissipation condition of the industrial computer, avoiding the one-sidedness of judging the heat dissipation condition based on a single temperature parameter, and providing an accurate data basis for subsequent heat dissipation control; the heat dissipation demand prediction model trained based on a large amount of historical data can more accurately predict the comprehensive thermal impact index according to the current load conditions and real-time parameters such as the fan speed, predict the heat dissipation demand in advance, reduce the lag of heat dissipation control, and improve the dynamic response speed of the temperature control system. According to the comparison between the prediction results and the safety threshold, the PID control algorithm is used to adjust the heat dissipation control strategy of the fan speed, thereby realizing intelligent regulation of heat dissipation; by comparing the actual and predicted comprehensive thermal impact indicators, when the actual indicator is greater than the predicted indicator, a prompt message for cleaning the fan dust is generated in time, thereby realizing early warning of heat dissipation failures, helping users to promptly discover and solve heat dissipation problems caused by fan dust accumulation, and avoiding more serious failures of the industrial computer caused by poor heat dissipation and component damage caused by excessive temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a schematic diagram of an industrial computer control method based on artificial intelligence described in the present invention. DETAILED DESCRIPTION

[0044] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0045] The following description sets forth numerous specific details to facilitate a thorough understanding of the present invention. The embodiments described are merely a portion of the embodiments of the present invention, rather than all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0047] One embodiment of the present invention provides an artificial intelligence-based industrial computer control method, the method comprising:

[0048] Obtain parameters of key heat-generating components of industrial computers and construct comprehensive thermal impact indicators for industrial computers;

[0049] Establish a heat dissipation demand prediction model based on the comprehensive thermal impact index of industrial computers;

[0050] Formulate a heat dissipation control strategy based on the comparison results between the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index;

[0051] According to the thermal impact comprehensive index after heat dissipation predicted by the heat dissipation control strategy, if the actual thermal impact comprehensive index is greater than the predicted thermal impact comprehensive index after heat dissipation, a prompt message for cleaning dust from the cooling fan of the industrial computer is generated.

[0052] The working principle and effect of the above technical solution are as follows: the comprehensive thermal impact index comprehensively considers multiple factors such as the various heat-generating components and heat dissipation parts within the industrial computer, as well as the internal and external ambient temperatures. It can accurately assess the heat dissipation status of the industrial computer, avoiding the one-sided judgment of the heat dissipation status based on a single temperature parameter, and providing an accurate data foundation for subsequent heat dissipation control. The heat dissipation demand prediction model, trained based on a large amount of historical data, can relatively accurately predict the comprehensive thermal impact index based on the current load and real-time parameters such as fan speed, predict heat dissipation demand in advance, reduce the lag of heat dissipation control, and improve the dynamic response speed of the temperature control system. Based on the comparison of the predicted results with the safety threshold, the PID control algorithm is used to adjust the heat dissipation control strategy of the fan speed, realizing intelligent heat dissipation regulation. By comparing the actual and predicted comprehensive thermal impact indexes, when the actual index exceeds the predicted index, a prompt message is promptly generated to clean the fan dust, providing an early warning of heat dissipation failures, helping users to promptly identify and resolve heat dissipation problems caused by fan dust accumulation, and avoiding more serious failures such as IPC performance degradation caused by poor heat dissipation and component damage caused by excessive temperature.

[0053] In one embodiment of the present invention, parameters of key heat-generating components of an industrial computer are obtained to construct a comprehensive thermal impact index of the industrial computer, including:

[0054] Obtain parameters of key heat-generating components of the industrial computer, including CPU temperature, GPU temperature, memory chip temperature, heat sink temperature, temperature difference between the two ends of the heat pipe, fan speed, GPU utilization, GPU load, CPU utilization, and CPU load;

[0055] Get the CPU temperature through the temperature sensor integrated inside the CPU;

[0056] Get the GPU temperature through the temperature sensor attached to the GPU surface;

[0057] Monitor the memory chip temperature through the temperature sensor located at the memory chip on the memory module;

[0058] Monitor the heat sink temperature by installing a temperature sensor on the top of the heat sink fins;

[0059] The temperature difference between the two ends of the heat pipe is monitored by temperature sensors installed at both ends of the heat pipe;

[0060] The internal and external ambient temperatures of the industrial computer are collected through temperature sensors;

[0061] Use hardware monitoring tools to obtain fan speed, GPU usage, GPU load, CPU usage, and CPU load data;

[0062] Record the timestamp of each data collection for subsequent time series analysis;

[0063] The thermal impact comprehensive index of the industrial computer is constructed by weighted summing the collected key heating component parameters, and the weight coefficients of the key heating component parameters are determined according to the performance of the industrial computer.

[0064] Use temperature sensors to collect the temperatures of key heat-generating components such as CPU, GPU memory, etc., and record them as At the same time, sensors are set at the joints between the heat sink and the heating component and on the top of the fins to obtain the heat sink temperature. Install sensors at both ends of the heat pipe to record the temperature at both ends of the heat pipe , collect the internal ambient temperature of the industrial computer through the ambient temperature sensor and external ambient temperature , use hardware monitoring tools to obtain fan speed And the CPU usage of the industrial computer running the program , GPU usage Load data.

[0065] ;

[0066] Among them, H represents the comprehensive index of thermal impact, and Represent the weight coefficients respectively.

[0067] The working principle and effect of the above technical solution are: the collected key heat-generating component parameters such as CPU temperature, GPU temperature, memory particle temperature, heat sink temperature, temperature difference between the two ends of the heat pipe, fan speed, GPU usage, GPU load, CPU usage, CPU load and internal and external ambient temperature are used to construct a comprehensive thermal impact index of the industrial computer through weighted summation. The weight coefficients of the key heat-generating components are not fixed, but are determined according to the performance of the industrial computer. For industrial computers that mainly perform CPU calculations, the weight coefficients of CPU-related parameters (such as CPU temperature, CPU usage, and CPU load) will be relatively large; for industrial computers that focus on graphics processing, the weight coefficients of GPU-related parameters are higher. By determining the weight coefficients of key heat-generating components based on the performance of the industrial computer, it is possible to more accurately reflect the actual thermal impact of industrial computers with different performance under various working conditions, and provide accurate data support for subsequent heat dissipation analysis and control.

[0068] In one embodiment of the present invention, the weight coefficients of the key heating component parameters are determined based on the performance of the industrial computer, including:

[0069] The process of calculating the weight coefficient of the comprehensive thermal impact index is divided into a target layer, a criterion layer, and an indicator layer. The target layer is used to determine the weight coefficient of the comprehensive thermal impact index. The criterion layer includes CPU performance, GPU performance, memory performance, heat sink cooling capacity, heat pipe cooling capacity, internal environment impact, and external environment impact. The indicator layer corresponds to the temperature parameter.

[0070] For industrial control hosts with different performance, the relative importance of each criterion is analyzed, the host performance parameters are quantitatively analyzed, and a judgment matrix is ​​constructed;

[0071] The maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated using the eigenroot method. After normalization, the eigenvector is the weight vector of each criterion relative to the target layer.

[0072] The judgment matrix is ​​tested for consistency, the consistency index is calculated, and the corresponding average random consistency index is found. Then the consistency ratio is calculated. When the consistency ratio is less than 0.1, the judgment matrix is ​​considered to have satisfactory consistency. Otherwise, the judgment matrix needs to be readjusted.

[0073] The working principle and effect of the above technical solution are as follows: through the structured process of hierarchical analysis method, various factors affecting the comprehensive thermal impact index are taken into account, and the analysis is gradually refined from different levels, making the determination of the weight coefficient more scientific and reasonable; the relative importance of each criterion is analyzed for industrial control hosts with different performance, making the weight determination method highly universal and targeted. Whether it is an industrial control host mainly based on CPU calculations or a host focusing on GPU graphics processing, the weight vector that meets its performance characteristics can be accurately determined by adjusting the judgment matrix construction process, thereby providing a practical basis for subsequent heat dissipation analysis and control; it avoids the situation where the weight coefficient is unreasonable due to inconsistent judgment matrices, making the determination process of the weight coefficient of the comprehensive thermal impact index more rigorous, laying a solid foundation for subsequent thermal analysis, heat dissipation strategy formulation and other work based on the weight coefficient, and improving the stability and reliability of the entire industrial control computer heat dissipation control method.

[0074] In one embodiment of the present invention, a heat dissipation demand prediction model is established based on the comprehensive heat impact index of the industrial computer, including:

[0075] Acquire a historical data set, the historical data set including historical key heat-generating component parameters of the industrial computer and corresponding comprehensive thermal impact indicators;

[0076] The historical data set is divided into a training set and a validation set. The training set is put into the neural network model for training until the set model training end conditions are met, and finally a heat dissipation demand prediction model is obtained;

[0077] Calculate the prediction period, and when the time reaches the prediction period, predict the temperature of the industrial computer through the established heat dissipation demand prediction model.

[0078] In one embodiment of the present invention, calculating the prediction period includes:

[0079] In order to obtain the absolute performance change index of the industrial computer, we obtain the difference between the CPU usage at the current moment and the previous moment, then obtain the difference between the GPU usage at the current moment and the previous moment, calculate the sum of the squares of the two differences, and then calculate the square root of the sum of the squares, which is , represents the modulus of the "change vector" in two-dimensional space. It represents the combined intensity of changes in CPU and GPU usage. Regardless of the direction of change (positive or negative), only the magnitude is considered. The square root is multiplied by the weight coefficient β to obtain the combined intensity of changes in CPU and GPU usage. By adjusting β, the weight of the absolute fluctuation on the prediction period can be controlled. Therefore, the evaluation coefficient of the intensity of short-term sharp fluctuations in industrial computer resource usage, that is, the instantaneous fluctuation intensity, can be expressed as:

[0080] ;

[0081] Obtain the average CPU usage over a preset time period. Divide the difference between the current and previous CPU usage by the quotient to obtain the quotient. This quotient is then added to the quotient of the difference between the current and previous GPU usage and the average GPU usage over the preset time period. The absolute value of this sum is taken to obtain the proportional change relative to the historical mean. This is then multiplied by the weight coefficient σ to capture long-term trend deviations. The larger σ is, the more sensitive the system is to relative deviations. For example, in scenarios with unstable resource usage baselines (such as cloud computing environments), σ can be increased to emphasize trend changes; in scenarios with stable baselines (such as embedded systems), σ can be reduced to rely primarily on absolute fluctuations. Therefore, the deviation of industrial computer resource fluctuations from the long-term average level, i.e., the evaluation coefficient for long-term trend deviation, can be expressed as:

[0082] ;

[0083] In order to achieve more comprehensive and robust adaptive control, the evaluation coefficient of instantaneous fluctuation intensity is added to the evaluation coefficient of long-term trend deviation to obtain the overall evaluation coefficient, namely:

[0084] ;

[0085] In order to avoid excessive adjustment of the prediction period, we then obtain the difference between the GPU usage at the current moment and the previous moment, calculate the sum of the squares of the two differences, and then calculate the square root of the sum of the squares, which is , reduce the impact of the β term on the prediction period, that is, the impact of excessive increase, obtain the average value of the CPU usage in the past preset time period, divide the difference between the current and previous CPU usage by it to obtain the quotient, and then add it to the quotient of the difference between the current and previous GPU usage and the average value of the GPU usage in the past preset time period, and take the absolute value of the whole to reduce the impact of the σ term on the prediction period, that is, the impact of excessive increase. Combine the parts that suppress the β term and the parts that suppress the σ term to obtain the overall suppression coefficient, namely:

[0086] ;

[0087] In order to avoid the denominator being 0, and when there is no fluctuation , the denominator degenerates to 1, which is consistent with basic logic and represents the default stable state of the system (no adjustment is required when there is no fluctuation). The overall suppression coefficient is added with 1. The overall evaluation coefficient and the overall suppression coefficient are combined to obtain the initial period adjustment coefficient, which is:

[0088] ;

[0089] In order to convert the fluctuation intensity into the compression coefficient of the forecast period, the stronger the fluctuation, the shorter the period, and obtain the overall period adjustment coefficient:

[0090] ;

[0091] Then the final expression of the forecast period model can be expressed as:

[0092] ;

[0093] in, represents the adjusted forecast period, represents the basic forecast period, Indicates the difference in CPU usage between the current moment and the previous moment. Indicates the difference between the GPU usage at the current moment and the previous moment, Indicates the average value of CPU usage during the preset time period. represents the average GPU usage rate in the past preset time period, β represents the first weight coefficient, and σ represents the second weight coefficient.

[0094] The working principle and effect of the above technical solution are: it can adjust the prediction cycle according to the real-time status of the industrial computer, and Incorporating this into the formula and calculating the difference in change by taking the square root of the sum of the squares can fully reflect the degree of fluctuation in CPU and GPU usage. Any significant change in either side can be captured, providing a basis for adjusting the prediction period. The greater the fluctuation in CPU and GPU usage, the shorter the prediction period. Considering the rate of change and , combined with the average usage rate, it can be determined whether the current change deviates from the normal state. If the CPU usage change value is small in a short period of time, but the change rate is large compared with the average usage rate, it also indicates that the load is unstable. At this time, the prediction period also needs to be adjusted. The greater the CPU and GPU usage deviates from the average usage rate, the shorter the prediction period. The weight coefficients β and σ can flexibly adjust the impact of the change difference and change rate on the prediction period according to actual conditions, thereby enhancing the adaptability of the formula. By normalizing the denominator and constructing the overall formula in an inverse form, the adjustment factor is ensured to be reasonable. When the load changes greatly, the prediction period is quickly shortened, and the heat dissipation demand is followed up in a timely manner. When the load is stable, the prediction period is extended, unnecessary calculations are reduced, and the overall operation efficiency of the system is improved. Avoid frequently adjusting the fan speed based on the prediction. The fan speed is adjusted only when necessary to reduce the wear of the fan motor and extend the fan service life.

[0095] In one embodiment of the present invention, a heat dissipation control strategy is formulated based on a comparison result of a predicted comprehensive heat impact index with a preset safety threshold of the comprehensive heat impact index, including:

[0096] Comparing the predicted comprehensive heat dissipation impact index with the preset comprehensive heat impact index;

[0097] If the predicted comprehensive heat dissipation impact index is greater than the preset comprehensive heat impact index, the speed of the heat dissipation fan is adjusted through a control algorithm.

[0098] The calculation formula for the fan speed adjustment ΔR is:

[0099] ;

[0100] in, and are the proportional, integral and differential coefficients respectively, represents the predicted comprehensive index of thermal impact, represents the preset safety threshold of the comprehensive thermal impact indicator, ΔR represents the fan speed adjustment amount, and t represents the time variable, which represents the time from the beginning of the prediction period to the current moment.

[0101] The working principle and effect of the above technical solution are: timely response to heat dissipation needs, through real-time comparison and prediction of comprehensive thermal impact indicators and safety thresholds, and immediately starting the PID control algorithm when the threshold is exceeded, it can quickly respond to the heat dissipation needs of the industrial computer, improve the heat dissipation response speed, and take timely measures in the early stage of thermal problems, reduce the lag of heat dissipation needs, and avoid performance degradation or hardware damage of the industrial computer due to untimely heat dissipation.

[0102] In one embodiment of the present invention, based on the comprehensive heat impact index after heat dissipation predicted by the heat dissipation control strategy, if the actual comprehensive heat impact index is greater than the predicted comprehensive heat impact index after heat dissipation, a prompt message for cleaning dust from the heat dissipation fan of the industrial computer is generated, including:

[0103] Obtain the predicted comprehensive index value of thermal impact after heat dissipation;

[0104] Use the temperature sensor installed on the industrial computer to obtain the actual thermal impact comprehensive index value of the current industrial computer after heat dissipation;

[0105] According to the predicted comprehensive index value of heat impact after heat dissipation and the actual comprehensive index value of heat impact after heat dissipation, the cleaning trigger coefficient K is calculated with the help of the cleaning trigger coefficient model. When the cleaning trigger coefficient K is greater than the first preset threshold and When it is greater than zero, a gradient warning signal is generated;

[0106] If the gradient warning signal lasts for three prediction cycles, a fan cleaning prompt message is output to the display of the industrial computer.

[0107] The deviation between the actual heat impact index and the predicted value is divided by the comprehensive heat impact index after the predicted heat dissipation to normalize the instantaneous heat dissipation deviation, reflecting the relative proportion of the current heat dissipation effect deviating from the predicted value. Then, the instantaneous heat dissipation deviation factor is obtained by multiplying it by the weight α to adjust the influence weight of the current deviation on the trigger coefficient K. The specific expression can be expressed as follows:

[0108] ;

[0109] The integral in quantifies the fan's continuous adjustment efforts during the cycle. If the fan runs at high speed for a long time (Δω is high), it indicates that the cooling system is under great pressure and needs to trigger cleaning to reduce the load. The exponential function makes the recent adjustment have a greater impact than the early adjustment ( The larger the value, the faster the old data decays), which is consistent with the engineering intuition that "the more recent the behavior, the more relevant it is"; This is to ensure that the speed increments of different fan models are comparable (for example, the physical meaning of the same proportional increments of fans rated at 5000RPM and 10000RPM is the same). Therefore, the expression for the speed cumulative load factor can be expressed as:

[0110] ;

[0111] A high frequency of ΔH > 0 indicates that the system has been in a critical heat dissipation state for a long time, which may indicate problems such as inadequate heat dissipation design or dust accumulation. Preemptive cleaning is required. The "last J hours" factor focuses on short-term history to avoid interference from stale data (for example, anomalies from a week ago are irrelevant to the current data). Using a proportional form (rather than an absolute number) avoids deviations caused by different sampling frequencies (for example, sampling every minute vs. every hour). Therefore, the expression for the historical anomaly frequency factor can be expressed as:

[0112] ;

[0113] Therefore, the expression of the cleaning trigger coefficient model can be expressed as:

[0114] ;

[0115] in, That is, the difference between the actual thermal impact comprehensive index value and the predicted thermal index, In order to predict the comprehensive index of thermal impact after heat dissipation, is the maximum rated speed of the fan, for The fan speed increment at each moment, For the last J hours The number of times, is the total number of sampling times, and is the weighting coefficient, is the speed influence attenuation factor, Indicates the starting time of the forecast period, which is different from the current time The time zone of integration is determined together .

[0116] The working principle and effect of the above technical solution are: Instant thermal deviation Relative deviation using Rather than an absolute value, eliminating the dimensional differences under different working conditions; when When the heat dissipation is good, the same The contribution value is greater, strengthening low-load anomaly detection; it can quickly respond to sudden heat dissipation failures (such as fan stoppage) and avoid misjudgment in high-load scenarios (because it allows larger absolute temperature fluctuations); long-term load accumulation items middle Quantify the cumulative speed increment to reflect the continuous overload operation; through exponential decay Achieve nonlinear saturation characteristics to avoid infinite accumulation; can capture gradual degradation (such as fan performance degradation caused by slow accumulation of dust); Adjust the historical impact weight ( When increasing, focus on recent data); Measure the statistical probability of abnormal events, identify intermittent faults (such as occasional poor heat dissipation caused by dust), and suppress single false triggers (multiple abnormalities are required to significantly increase the K value).

[0117] In one embodiment of the present invention, the artificial intelligence-based industrial computer control system includes:

[0118] Build a comprehensive thermal impact index module to obtain the parameters of key heat-generating components of industrial computers and build a comprehensive thermal impact index for industrial computers;

[0119] Establish a heat dissipation demand prediction model module, which is used to establish a heat dissipation demand prediction model based on the comprehensive thermal impact indicators of industrial computers;

[0120] The heat dissipation control module is used to formulate a heat dissipation control strategy based on the comparison result of the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index;

[0121] The prompt module is used to generate a prompt message to clean the dust of the industrial computer cooling fan if the actual comprehensive heat impact index is greater than the predicted comprehensive heat impact index after cooling according to the heat dissipation control strategy.

[0122] One embodiment of the present invention provides an artificial intelligence-based industrial computer control system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the artificial intelligence-based industrial computer control method when executing the program.

[0123] One embodiment of the present invention is a computer program product, comprising a computer program and / or instructions, characterized in that when the computer program and / or instructions are executed by a processor, the steps of the industrial computer control method based on artificial intelligence are implemented.

[0124] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An industrial computer control method based on artificial intelligence, characterized in that: The method comprises: Obtain parameters of key heat-generating components of industrial computers and construct comprehensive thermal impact indicators for industrial computers; A heat dissipation demand prediction model is established based on the comprehensive thermal impact indicators of industrial computers, including: Acquire a historical data set, the historical data set including historical key heat-generating component parameters of the industrial computer and corresponding comprehensive thermal impact indicators; The historical data set is divided into a training set and a validation set. The training set is put into the neural network model for training until the set model training end conditions are met, and finally a heat dissipation demand prediction model is obtained; Calculate the prediction period. When the time reaches the prediction period, the temperature of the industrial computer is predicted by the established heat dissipation demand prediction model. The prediction period is calculated by the prediction period model: Specifically, the prediction cycle model is: ； in, represents the adjusted forecast period, represents the basic forecast period, Indicates the difference in CPU usage between the current moment and the previous moment. Indicates the difference between the GPU usage at the current moment and the previous moment, Indicates the average value of CPU usage during the preset time period. represents the average GPU usage rate in the past preset time period, β represents the first weight coefficient, and σ represents the second weight coefficient; Formulate a heat dissipation control strategy based on the comparison results between the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index; According to the thermal impact comprehensive index after heat dissipation predicted by the heat dissipation control strategy, if the actual thermal impact comprehensive index is greater than the predicted thermal impact comprehensive index after heat dissipation, a prompt message for cleaning dust from the cooling fan of the industrial computer is generated.

2. The artificial intelligence-based industrial computer control method according to claim 1, characterized in that: Obtain the parameters of key heat-generating components of industrial computers and construct comprehensive thermal impact indicators for industrial computers, including: Obtain parameters of key heat-generating components of the industrial computer, including CPU temperature, GPU temperature, memory chip temperature, heat sink temperature, temperature difference between the two ends of the heat pipe, fan speed, GPU utilization, GPU load, CPU utilization, and CPU load; Record the timestamp of each data collection for subsequent time series analysis; The thermal impact comprehensive index of the industrial computer is constructed by weighted summing the collected key heating component parameters, and the weight coefficients of the key heating component parameters are determined according to the performance of the industrial computer.

3. According to the artificial intelligence-based industrial computer control method of claim 2, the weight coefficients of the key heating component parameters are determined according to the performance of the industrial computer, including: The process of determining the weight coefficient of the comprehensive thermal impact index is divided into a target layer, a criterion layer, and an indicator layer. The target layer is used to determine the weight coefficient of the comprehensive thermal impact index. The criterion layer includes CPU performance, GPU performance, memory performance, heat sink cooling capacity, heat pipe cooling capacity, internal environment impact, and external environment impact. The indicator layer corresponds to the temperature parameter. For industrial control hosts with different performance, the relative importance of each criterion is analyzed, the host performance parameters are quantitatively analyzed, and a judgment matrix is ​​constructed; The maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated using the eigenroot method. After normalization, the eigenvector is the weight vector of each criterion relative to the target layer. The judgment matrix is ​​tested for consistency, the consistency index is calculated, and the corresponding average random consistency index is found. Then the consistency ratio is calculated. When the consistency ratio is less than 0.1, the judgment matrix is ​​considered to have satisfactory consistency. Otherwise, the judgment matrix needs to be readjusted.

4. The artificial intelligence-based industrial computer control method according to claim 1, characterized in that: The forecast period is calculated by a forecast period model.

5. The artificial intelligence-based industrial computer control method according to claim 1, characterized in that: Formulate a heat dissipation control strategy based on the comparison between the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index, including: Comparing the predicted comprehensive heat dissipation impact index with the preset comprehensive heat impact index; If the predicted comprehensive heat dissipation impact index is greater than the preset comprehensive heat impact index, the speed of the heat dissipation fan is adjusted through a control algorithm.

6. The artificial intelligence-based industrial computer control method according to claim 1, characterized in that: Based on the thermal impact comprehensive index after heat dissipation predicted by the heat dissipation control strategy, if the actual thermal impact comprehensive index is greater than the predicted thermal impact comprehensive index after heat dissipation, a prompt message is generated to clean dust from the industrial computer's heat dissipation fan, including: Obtain the predicted comprehensive index value of thermal impact after heat dissipation; Use the temperature sensor installed on the industrial computer to obtain the actual thermal impact comprehensive index value of the current industrial computer after heat dissipation; According to the predicted comprehensive index value of heat impact after heat dissipation and the actual comprehensive index value of heat impact after heat dissipation, the cleaning trigger coefficient K is calculated with the help of the cleaning trigger coefficient model. When the cleaning trigger coefficient K is greater than the first preset threshold and When it is greater than zero, a gradient warning signal is generated. The expression of the cleaning trigger coefficient model is expressed as: ； in, That is, the difference between the actual thermal impact comprehensive index value and the predicted thermal index, In order to predict the comprehensive index of thermal impact after heat dissipation, is the maximum rated speed of the fan, is the fan speed increment at time t, Indicates that within the preset period The number of times, is the total number of sampling times, is the weighting coefficient, is the speed influence attenuation factor, Indicates the starting time of the forecast period, which is different from the current time The time zone of integration is jointly determined [ , ]; If the gradient warning signal lasts for three prediction cycles, a fan cleaning prompt message is output to the display of the industrial computer.

7. An industrial computer control system based on artificial intelligence, characterized in that: The system comprises: Build a comprehensive thermal impact index module to obtain the parameters of key heat-generating components of industrial computers and build a comprehensive thermal impact index for industrial computers; Establish a heat dissipation demand prediction model module, which is used to establish a heat dissipation demand prediction model based on the comprehensive thermal impact index of the industrial computer, including: Acquire a historical data set, the historical data set including historical key heat-generating component parameters of the industrial computer and corresponding comprehensive thermal impact indicators; The historical data set is divided into a training set and a validation set. The training set is put into the neural network model for training until the set model training end conditions are met, and finally a heat dissipation demand prediction model is obtained; Calculate the prediction period. When the time reaches the prediction period, the temperature of the industrial computer is predicted by the established heat dissipation demand prediction model. The prediction period is calculated by the prediction period model: Specifically, the prediction cycle model is: ； in, represents the adjusted forecast period, represents the basic forecast period, Indicates the difference in CPU usage between the current moment and the previous moment. Indicates the difference between the GPU usage at the current moment and the previous moment, Indicates the average value of CPU usage during the preset time period. represents the average GPU usage rate in the past preset time period, β represents the first weight coefficient, and σ represents the second weight coefficient; The heat dissipation control module is used to formulate a heat dissipation control strategy based on the comparison result of the predicted comprehensive heat impact index and the preset safety threshold of the comprehensive heat impact index; The prompt module is used to generate a prompt message to clean the dust of the industrial computer cooling fan if the actual comprehensive heat impact index is greater than the predicted comprehensive heat impact index after cooling according to the heat dissipation control strategy.

8. An industrial computer control system based on artificial intelligence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer program product comprising a computer program and / or instructions, characterized in that When the computer program and / or instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images