Abnormal monitoring platform and system of explosion-proof electrical test bench based on Internet of Things

Abstract

The present invention relates to the field of data processing technology, and in particular to an abnormal monitoring platform and system for explosion-proof electrical test benches based on the Internet of Things. The platform includes: a data acquisition module, which obtains various parameters of each task of the same type of the target test bench and each reference test bench; a data processing module, which determines the reference degree, reference distance measurement coefficient, distance measurement coefficient, final distance measurement coefficient and local reachable density in turn, and obtains the outlier factor through the LOF algorithm based on the local reachable density; an analysis and early warning module, which issues an abnormal early warning prompt in response to the outlier factor being greater than the abnormal threshold. The outlier factor of each sampling point in the first task is obtained through the LOF algorithm based on the local reachable density as a weight, which can more accurately identify abnormal sampling points, avoid false alarms of normal data points as abnormal data points, and make the monitoring results of the explosion-proof electrical test bench more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an abnormality monitoring platform and system for an explosion-proof electrical appliance test bench based on the Internet of Things. Background Art

[0002] The explosion-proof electrical appliance test bench is a device specially used to test and verify the performance of explosion-proof electrical appliances, aiming to ensure that explosion-proof electrical appliances can operate safely and reliably in potentially explosive environments. Explosion-proof electrical appliances are widely used in industries such as petroleum, chemical, coal mining, and pharmaceuticals. There are a large number of flammable and explosive substances in these industries. Once an accident occurs, it will cause great harm and loss to people and the economy. Since the performance of explosion-proof electrical appliances is tested through the explosion-proof electrical appliance test bench, it is also very important to monitor the performance of the explosion-proof electrical appliance test bench itself.

[0003] The patent document with announcement number CN218240270U discloses an explosion-proof electrical protection performance test bench, including a main body, a test bench installed on the front of the main body, a group of vertical rods installed on the right side of the test bench, and the vertical rods are located on the right side of the main body, a group of lifting frames installed on the right side of the vertical rods, a lifting motor installed inside the test bench, a cleaner installed on the top of the main body, and the cleaner is located on the left side of the vertical rods. By installing the vertical rods, the staff can operate the control button to control the start of the lifting motor, so that the lifting motor can drive the power wheel to rotate and the steel cable to extend and retract, so that the steel cable can cooperate with the support rod to drive the rolling wheel and the lifting frame to move up and down, and at the same time, the support wheel provides support for the lifting frame, so that a group of lifting frames can cooperate with the connecting rod to drive the equipment tested on its top to move up and down, so that before testing the explosion-proof electrical protection performance test, the height of the tested equipment can be automatically raised and lowered conveniently, saving the physical strength of the staff.

[0004] However, the above patent document does not mention how to monitor the explosion-proof electrical test bench itself to ensure the accuracy of the abnormal monitoring results of the explosion-proof electrical test bench; in the prior art, the LOF algorithm can be used to monitor the explosion-proof electrical test bench, but since the distribution uniformity of each monitoring parameter in different intervals is different, the traditional LOF algorithm obtains the local outlier factor through the local density, which will cause the actual normal data points to have a high local outlier factor due to uneven distribution, and in the subsequent judgment, the false alarm is an abnormal data point, resulting in inaccurate monitoring results of the explosion-proof electrical test bench. Summary of the invention

[0005] In order to solve the problem that the traditional LOF algorithm obtains the local outlier factor through the local density, which may cause the local outlier factor of the actual normal data points to be high due to the uneven distribution, and false alarms are abnormal data points in subsequent judgments, resulting in inaccurate monitoring results of the explosion-proof electrical appliance test bench, the present invention provides an abnormal monitoring platform and system for the explosion-proof electrical appliance test bench based on the Internet of Things.

[0006] In the first aspect, the present invention provides an abnormality monitoring platform for explosion-proof electrical appliance test benches based on the Internet of Things, which adopts the following technical solutions:

[0007] The abnormality monitoring platform of explosion-proof electrical test bench based on Internet of Things includes: a data acquisition module, which obtains various parameters of each task of the same type of the target test bench and each reference test bench; a data processing module, which takes each task of each reference test bench as a candidate task, and determines the reference degree of the candidate task according to the mean of the DTW distance between each task of the target test bench and the target parameters of the candidate task; takes the current task of the target test bench as the first task, and determines the reference distance measurement coefficient of the candidate task to each sampling point in the first task within the target parameter according to the target parameters of each sampling point in the candidate task and the first task; The target parameters of each sampling point in each task of the test bench are used to determine the distance measurement coefficient of each sampling point in the first task within the target parameters; according to the distance measurement coefficient, the reference degree of all candidate tasks and the reference distance measurement coefficient corresponding to all candidate tasks, the final distance measurement coefficient of each sampling point in the first task within the target parameters is determined; according to the final distance measurement coefficient within all parameters, the local reachable density of each sampling point in the first task is determined, and the outlier factor of each sampling point in the first task is obtained through the LOF algorithm according to the local reachable density; the analysis and warning module issues an abnormal warning prompt in response to the outlier factor being greater than the abnormal threshold.

[0008] By using the DTW distance to compare the task data of the target test bench and the reference test bench, anomalies in time series data can be more accurately identified; using known data as a comparison basis, the reference degree of the candidate task is determined to more accurately identify potential abnormal situations; the reference distance measurement coefficient of the candidate task to each sampling point in the first task is calculated, and the reference degree of all candidate tasks is integrated to adapt the final distance measurement coefficient of each sampling point to improve the adaptability to complex data; the outlier factor of each sampling point is obtained through the LOF algorithm based on the local reachable density obtained in the present invention, so that the value of the outlier factor is more accurate, and the situation of false alarming of the sampling point as an abnormal data point is reduced; when the outlier factor exceeds the set abnormal threshold, an early warning is issued in time, which can quickly respond to possible equipment failures or abnormalities, thereby improving the safety and reliability of the system.

[0009] Furthermore, the various parameters include temperature parameters, pressure parameters, vibration parameters, current parameters and voltage parameters of the explosion-proof electrical appliance test bench.

[0010] Furthermore, the reference degree satisfies the following relationship:

[0011] ; In the formula, For the Reference test bench In the second task The reference degree of the item parameter, is the number of target testbed tasks, For the target test bench The second task and Reference test bench The second task The DTW distance between the item parameters, Linear normalization function.

[0012] By using a linear normalization function to convert the DTW distance into a standardized metric, it helps to avoid the impact caused by different parameter scales, thereby improving the fairness of the comparison; using the mean to average the DTW distance can effectively reduce the impact of abnormal data in a single task on the reference degree.

[0013] Furthermore, the reference distance measurement coefficient satisfies the following relationship:

[0014] ; In the formula, For the Reference test bench The second task is the first task in the The sampling point is The reference distance metric coefficient within the term parameter, For the Reference test bench The number of sampling points in the task, For the first task The sampling point is The value of the item parameter, For the Reference test bench In the second task The sampling point is The value of the item parameter, Linear normalization function, is a natural exponential function.

[0015] The natural exponential function and linear normalization function ensure accurate identification and quantification of abnormal situations, thereby improving the accuracy and reliability of abnormal monitoring; by comparing each sampling point with multiple sampling points of the reference test bench and through exponential decay and normalization processing, normal fluctuations and abnormal changes can be effectively distinguished, thereby enhancing the robustness and detection accuracy of the system.

[0016] Furthermore, the distance measurement coefficient satisfies the following relationship:

[0017] ; In the formula, For the first task The sampling point is The distance metric coefficient within the term parameter, is the number of target testbed tasks, For the target test bench The number of sampling points in the task, For the first task The sampling point is The value of the item parameter, For the target test bench The first task The sampling point is The value of the item parameter, Linear normalization function, is a natural exponential function.

[0018] By calculating the exponential decay distance between the sampling points in each task of the target test bench and the current sampling point in terms of parameter values ​​and performing linear normalization, the distance measurement coefficient of each sampling point is accurately quantified, thereby improving the accuracy and robustness of anomaly detection.

[0019] Furthermore, the final distance metric coefficient satisfies the following relationship:

[0020] ; In the formula, For the first task The sampling point is The final distance metric coefficient within the term parameter, is the number of reference test rigs, For the The number of reference testbed tasks, For the Reference test bench In the second task The reference degree of the item parameter, For the Reference test bench The second task is the first task in the The sampling point is The reference distance metric coefficient within the term parameter, For the first task The sampling point is The distance measure coefficient within the term parameter.

[0021] By combining the distance measurement coefficients of the reference test bench and the target test bench and taking the reference degree of the reference test bench as the weight, the final distance measurement coefficient is calculated, thereby improving the accuracy and reliability of anomaly detection.

[0022] Furthermore, the local reachable density satisfies the following relationship:

[0023] ; In the formula, For the first task The local reachability density of the sampling points is is the number of parameter categories, is the number of sampling points within the preset local range, For the first task The sampling point is The final distance metric coefficient within the term parameter, For the first task The sampling point is The value of the item parameter, For the first task The local range of the sampling point The sampling point is The value of the item parameter.

[0024] By obtaining the local reachable density, the relative density of the target test bench in the local environment of a sampling point and its neighboring points can be effectively measured, which helps to identify outliers or dense areas in a specific area; by considering the influence of other data points within the local range of the target point, the structure of the local data can be more accurately reflected, which helps to improve the accuracy of data analysis and processing.

[0025] In the second aspect, the present invention provides an abnormality monitoring system for an explosion-proof electrical appliance test bench based on the Internet of Things, which adopts the following technical solutions:

[0026] The abnormality monitoring system of the explosion-proof electrical appliance test bench based on the Internet of Things comprises: an abnormality monitoring terminal of the explosion-proof electrical appliance test bench based on the Internet of Things and the abnormality monitoring platform of the explosion-proof electrical appliance test bench based on the Internet of Things.

[0027] By adopting the above technical solution, the above-mentioned abnormal monitoring platform of the explosion-proof electrical appliance test bench based on the Internet of Things and the abnormal monitoring terminal of the explosion-proof electrical appliance test bench based on the Internet of Things are integrated into an abnormal monitoring system of the explosion-proof electrical appliance test bench based on the Internet of Things, which is convenient to use.

[0028] The present invention has the following technical effects:

[0029] Through the means of data collection, processing, analysis and early warning, the monitoring accuracy, data processing capability and anomaly detection accuracy are significantly improved, the maintenance strategy is optimized, the cost is reduced, and the reliability and safety of the system are improved; then the outlier factor of each sampling point in the first task is obtained through the LOF algorithm based on the local reachable density as the weight, which can more accurately identify abnormal sampling points and avoid false alarms of normal data points as abnormal data points, making the monitoring results of the explosion-proof electrical test bench more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0031] Figure 1 It is a module block diagram of an abnormality monitoring platform of an explosion-proof electrical appliance test bench based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0034] The embodiment of the present invention provides an abnormality monitoring platform for explosion-proof electrical appliance test bench based on the Internet of Things. Figure 1 As shown, the abnormal monitoring platform of the explosion-proof electrical appliance test bench based on the Internet of Things includes a data acquisition module 110, a data processing module 120 and an analysis and early warning module 130, which are specifically described below:

[0035] It should be noted that in order to effectively identify the abnormal situation of the explosion-proof electrical test bench during the execution of the task, it is necessary to monitor the explosion-proof electrical test bench. When monitoring, the explosion-proof electrical test bench's own historical data is used as a reference to solve the problem of false alarms of unevenly distributed normal data points. Due to the small amount of its own data, it is impossible to effectively identify the data points that are actually normal but have a lower density and the data points that are actually abnormal but have a higher density, such as the frequently occurring same abnormal points and the actual normal points that occur less frequently. The data distribution frequency of the same model of explosion-proof electrical test bench when performing the same task has a certain similarity. Therefore, in order to improve the recognition of the data points that are actually normal but have a lower density and the data points that are actually abnormal but have a higher density, it is necessary to collect various parameters of each task of the same type of the explosion-proof electrical test bench and the reference test bench, so as to carry out subsequent abnormal monitoring of the explosion-proof electrical test bench.

[0036] The data acquisition module 110 obtains various parameters of each task of the same type of the target test bench and each reference test bench.

[0037] Specifically, the various parameters include temperature parameters, pressure parameters, vibration parameters, current parameters and voltage parameters of the explosion-proof electrical appliance test bench.

[0038] The temperature, pressure, vibration, current and voltage parameters of the explosion-proof electrical test bench are obtained through the temperature sensors, pressure sensors, vibration sensors, current sensors and voltage sensors in the abnormal monitoring platform.

[0039] The data processing module 120 determines the reference degree, reference distance measurement coefficient, distance measurement coefficient, final distance measurement coefficient and local reachable density in turn according to the parameters of each task of the same type of the target test bench and each reference test bench, and obtains the outlier factor through the LOF algorithm based on the local reachable density.

[0040] It should be noted that although the reference test bench and the target test bench have the same model, there are still individual differences. When the reference test bench performs the same task as the target test bench, the dynamic time warping (DTW) algorithm is used to obtain the similarity between the same parameters of the same type of tasks on different devices. The smaller the DTW distance between the same parameters of the reference test bench and the target test bench, the higher the similarity of the two task processes, and the higher the reference degree of the parameters of this task of the reference test bench.

[0041] Each task of each reference test bench is taken as a candidate task, and the reference degree of the candidate task is determined according to the mean of the DTW distance between each task of the target test bench and the target parameters of the candidate task.

[0042] Specifically, the reference degree satisfies the following relationship:

[0043] ;

[0044] In the formula, For the Reference test bench In the second task The reference degree of the item parameter, is the number of target testbed tasks, For the target test bench The second task and Reference test bench The second task The DTW distance between the item parameters, Linear normalization function.

[0045] Among them, when the target monitoring parameters in each task of the target test bench are The smaller the mean DTW distance of the target monitoring parameters in the task, the closer the target monitoring parameters of the target test bench in the current task are to the reference test bench. The more similar the target monitoring parameters are in the tasks, the more likely the reference test bench The more feasible the target monitoring parameters in the task are as a reference for calibrating the reference distance measurement coefficient.

[0046] It should be noted that in order to accurately evaluate whether there are any abnormalities at each sampling point in the current task (first task) of the target test bench, it is necessary to determine the reference metric distance coefficient. The reference metric distance coefficient measures the similarities or differences in the target parameters of these sampling points by comparing the target parameter values ​​of each sampling point in the candidate task and the first task, and helps identify which sampling points deviate from the normal range. In order to increase the local reachability density of sampling points that have a high degree of possibility of normal data points but a low actual local reachability density, a smaller reference distance metric coefficient needs to be set.

[0047] The current task of the target test bench is taken as the first task, and the reference distance measurement coefficient of the candidate task to each sampling point in the first task within the target parameter is determined according to the target parameters of each sampling point in the candidate task and the first task.

[0048] Specifically, the reference distance measurement coefficient satisfies the following relationship:

[0049] ;

[0050] In the formula, For the Reference test bench The second task is the first task in the The sampling point is The reference distance metric coefficient within the term parameter, For the Reference test bench The number of sampling points in the task, For the first task The sampling point is The value of the item parameter, For the Reference test bench In the second task The sampling point is The value of the item parameter, Linear normalization function, is a natural exponential function.

[0051] in, Indicates the target test bench The sampling point is The value of the parameter is relative to Reference test bench In the second task The sampling point is The closeness between the values ​​of the parameters of the first task The first parameter in the The closer the sampling point is to the Reference test bench Second task The more sampling points there are in the parameter, the greater the value of the Reference test bench Second task When the first task has the The higher the possibility that a sampling point is a normal data point, the smaller the reference distance measurement coefficient.

[0052] It should be noted that when the parameter value of the target test bench at a certain moment is closer to the target monitoring parameter value, the possibility that the corresponding parameter evaluated by the target test bench target parameter is normal data is higher, so the distance measurement coefficient should be lower.

[0053] According to the target parameters of each sampling point in each task of the target test bench, the distance measurement coefficient of each sampling point in the first task within the target parameter is determined.

[0054] Specifically, the distance measurement coefficient satisfies the following relationship:

[0055] ;

[0056] In the formula, For the first task The sampling point is The distance metric coefficient within the term parameter, is the number of target testbed tasks, For the target test bench The number of sampling points in the task, For the first task The sampling point is The value of the item parameter, For the target test bench The first task The sampling point is The value of the item parameter, Linear normalization function, is a natural exponential function.

[0057] in, Indicates the target test bench The sampling point is The value of the parameter is relative to the target test bench. In the second task The sampling point is The closeness between the values ​​of the parameters of the first task The first parameter in the The closer the sampling point is to the Reference test bench Second task The more sampling points there are in the parameter, the greater the value of the Reference test bench Second task When the first task has the The higher the probability that the sampling point is a normal data point, the smaller the reference distance measurement coefficient. The sampling point is The closer the value of the parameter is to the When the number of sampling points in the i-th parameter in the task is large, the higher the possibility that the sampling point is a normal data point, the higher the distance measurement coefficient.

[0058] It should be noted that when the reference degree of the reference task is higher, the target parameters of the reference test bench are more similar to those of the target test bench, and the reference distance metric coefficient can be used more for calculation. Otherwise, the distance metric coefficient is used more for calculation to obtain the final distance metric coefficient, which is used to weight the distance between sampling points to avoid false alarms of normal data points with low density.

[0059] According to the distance metric coefficient, the reference degrees of all candidate tasks and the reference distance metric coefficients corresponding to all candidate tasks, a final distance metric coefficient of each sampling point in the first task within the target parameter is determined.

[0060] Specifically, the final distance metric coefficient satisfies the following relationship:

[0061] ;

[0062] In the formula, For the first task The sampling point is The final distance metric coefficient within the term parameter, is the number of reference test rigs, For the The number of reference testbed tasks, For the Reference test bench In the second task The reference degree of the item parameter, For the Reference test bench The second task is the first task in the The sampling point is The reference distance metric coefficient within the term parameter, For the first task The sampling point is The distance measure coefficient within the term parameter.

[0063] in, Indicates that Reference test bench Second task The reference degree of the parameter is the weight, which is used to calibrate the final distance measurement coefficient. When the reference degree is higher, more reference can be made to the first Reference test bench history Execute the mission The final distance metric coefficient is calculated by using the parameters; when the feasibility is lower, the target test bench is used more. The final distance metric coefficient is calculated using the term parameters.

[0064] The local reachable density of each sampling point in the first task is determined according to the final distance metric coefficient within all parameters.

[0065] Specifically, the local reachable density satisfies the following relationship:

[0066] ;

[0067] In the formula, For the first task The local reachability density of the sampling points is is the number of parameter categories, is the number of sampling points within the preset local range, For the first task The sampling point is The final distance metric coefficient within the term parameter, For the first task The sampling point is The value of the item parameter, For the first task The local range of the sampling point The sampling point is The value of the item parameter.

[0068] Implementers can set the number of sampling points within the local area according to specific implementation circumstances, for example, 5.

[0069] in, Indicates the first task The sampling point is Parameters to the first task The local range of the sampling point The sampling point is Since there are many parameters to be monitored, Manhattan distance should be used as the distance metric to avoid sparsity caused by high dimensionality of monitoring data.

[0070] The outlier factor of each sampling point in the first task is obtained by using a local outlier factor (LOF) algorithm according to the local reachable density.

[0071] The LOF algorithm obtains the outlier factor of each sampling point in the first task to satisfy the following relationship:

[0072] ;

[0073] In the formula, For the first task The outlier factor of the sampling points, is the number of sampling points within the preset local range, For the first task The local range of the preset sampling point The local reachability density of the sampling points is For the first task The local reachability density of each sampling point.

[0074] The analysis and warning module 130 issues an abnormal warning prompt in response to the outlier factor being greater than the abnormal threshold.

[0075] When the outlier factor is greater than the abnormal threshold, the sampling point of the target test bench is marked as an abnormal data point, and the abnormal instruction is output in real time to the abnormal monitoring platform of the explosion-proof electrical test bench to promptly remind the staff to pay attention to the situation of the explosion-proof electrical test bench.

[0076] Implementers can set the exception threshold according to specific implementation circumstances, for example, 1.

[0077] The embodiment of the present invention also discloses an abnormality monitoring system of an explosion-proof electrical appliance test bench based on the Internet of Things, including an abnormality monitoring terminal of the explosion-proof electrical appliance test bench based on the Internet of Things and an abnormality monitoring platform of the explosion-proof electrical appliance test bench based on the Internet of Things in the present invention.

[0078] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0079] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. The abnormal monitoring platform of explosion-proof electrical test bench based on Internet of Things is characterized by: include: The data acquisition module obtains various parameters of each task of the same type of the target test bench and each reference test bench; The data processing module takes each task of each reference test bench as a candidate task, and determines the reference degree of the candidate task according to the mean of the DTW distance between each task of the target test bench and the target parameters of the candidate task, satisfying the following relationship: ; In the formula, For the Reference test bench In the second task The reference degree of the item parameter, is the number of target testbed tasks, For the target test bench The second task and Reference test bench The second task The DTW distance between the item parameters, Linear normalization function; taking the current task of the target test bench as the first task, according to the target parameters of each sampling point in the candidate task and the first task, determine the reference distance measurement coefficient of each sampling point in the first task within the target parameters, satisfying the following relationship: ; In the formula, For the Reference test bench The second task is the first task in the The sampling point is The reference distance metric coefficient within the term parameter, For the Reference test bench The number of sampling points in the task, For the first task The sampling point is The value of the item parameter, For the Reference test bench In the second task The sampling point is The value of the item parameter, is a natural exponential function; according to the target parameters of each sampling point in each task of the target test bench, the distance measurement coefficient of each sampling point in the first task within the target parameter is determined to satisfy the following relationship: ; In the formula, For the first task The sampling point is The distance metric coefficient within the term parameter, For the target test bench The number of sampling points in the task, For the target test bench The first task The sampling point is The value of the item parameter; According to the distance metric coefficient, the reference degrees of all candidate tasks and the reference distance metric coefficients corresponding to all candidate tasks, the final distance metric coefficient of each sampling point in the first task within the target parameter is determined to satisfy the following relationship: ; In the formula, For the first task The sampling point is The final distance metric coefficient within the term parameter, is the number of reference test rigs, For the The number of reference test bench tasks; according to the final distance metric coefficient within all parameters, the local reachability density of each sampling point in the first task is determined to satisfy the following relationship: ; In the formula, For the first task The local reachability density of the sampling points is is the number of parameter categories, is the number of sampling points within the preset local range, For the first task The local range of the sampling point The sampling point is The value of the item parameter; obtaining the outlier factor of each sampling point in the first task by the LOF algorithm according to the local reachable density; The analysis and warning module issues an abnormal warning prompt in response to the outlier factor being greater than the abnormal threshold.

2. The abnormality monitoring platform of the explosion-proof electrical appliance test bench based on the Internet of Things according to claim 1 is characterized in that: The various parameters include temperature parameters, pressure parameters, vibration parameters, current parameters and voltage parameters of the explosion-proof electrical appliance test bench.

3. The abnormal monitoring system of explosion-proof electrical test bench based on Internet of Things is characterized by: include: An abnormality monitoring terminal for an explosion-proof electrical appliance test bench based on the Internet of Things and an abnormality monitoring platform for an explosion-proof electrical appliance test bench based on the Internet of Things according to claim 1 or 2.

Images