Method, device and equipment for processing operation data of medical waste treatment equipment

Abstract

The invention provides a medical waste treatment equipment operation data processing method, device and equipment, and relates to the field of data processing. The treatment method comprises the following steps: acquiring current operation data of a plurality of medical waste treatment devices; preprocessing the current operation data to generate a plurality of groups of statistical index data; respectively inputting each group of statistical index data into a preset fault diagnosis model for fault diagnosis, and generating fault diagnosis result data corresponding to each group of statistical index data; wherein the preset fault diagnosis model is obtained by training a preset neural network model according to historical maintenance data; and according to the fault diagnosis result data and the historical maintenance data, generating maintenance plan data corresponding to each medical waste treatment device, and performing visual output display. According to the scheme, remote monitoring of the medical waste treatment equipment and rapid diagnosis and maintenance management after the equipment breaks down are achieved, and therefore the operation efficiency of the equipment is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method, device and equipment for processing operation data of medical waste treatment equipment. Background Art

[0002] Existing medical waste treatment equipment requires regular maintenance and management during use to ensure its normal operation and extend the life of the equipment. Traditional operation and maintenance management methods usually rely on manual records and on-site inspections, which are not only inefficient but also prone to data loss and errors, resulting in untimely equipment maintenance, inefficient troubleshooting, and reduced customer satisfaction. Summary of the invention

[0003] The present invention provides a method, device and equipment for processing the operation data of medical waste treatment equipment, which solves the problems of low maintenance efficiency, easy data loss and errors, untimely equipment maintenance and low fault handling efficiency in the maintenance process of existing medical waste treatment equipment.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] An embodiment of the present invention provides a method for processing operation data of medical waste treatment equipment, comprising:

[0006] Obtain current operating data of multiple medical waste treatment equipment;

[0007] Preprocessing the current operation data to generate multiple groups of statistical indicator data;

[0008] Input each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generate fault diagnosis result data corresponding to each group of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model based on historical maintenance data;

[0009] Based on the fault diagnosis result data and historical maintenance data, the maintenance plan data corresponding to each medical waste treatment equipment is generated and displayed visually.

[0010] Optionally, the current operation data is preprocessed to generate multiple sets of statistical indicator data, including:

[0011] Clean all the current running data, remove outliers, duplicate values, and missing values, and obtain a plurality of first pre-processed data;

[0012] Performing format conversion processing on the first preprocessed data to obtain second preprocessed data;

[0013] The second pre-processed data is integrated to generate multiple groups of statistical indicator data.

[0014] Optionally, the process of training a preset neural network model based on historical maintenance data includes:

[0015] Extracting features from the historical maintenance data to obtain multiple groups of initial training data;

[0016] Obtain the operating status data of medical waste treatment equipment;

[0017] Associating multiple groups of initial training data with the operating status data of medical waste treatment equipment to obtain target training data;

[0018] The preset neural network model is trained with target training data to obtain a preset fault diagnosis model.

[0019] Optionally, feature extraction is performed on the historical maintenance data to obtain multiple groups of initial training data, including:

[0020] Perform feature extraction processing on the historical maintenance data according to the statistical indicator data to obtain first feature data;

[0021] Performing feature extraction processing on the fault cause data in the historical maintenance data to obtain second feature data;

[0022] The first feature data and the second feature data are associated to obtain initial training data.

[0023] Optionally, a preset neural network model is trained using target training data to obtain a preset fault diagnosis model, including:

[0024] Input the target training data into the input layer of the preset neural network model for processing to obtain the first layer output;

[0025] According to the first layer output and the first layer weight, the hidden layer of the preset neural network model is input for processing to obtain the second layer output;

[0026] According to the second layer output and the second layer weight, input the output layer of the preset neural network model for processing to obtain the third layer output;

[0027] The first layer weights and the second layer weights are adjusted according to the third layer output until the square error criterion function corresponding to the third layer meets the target condition, thereby obtaining the preset fault diagnosis model.

[0028] Optionally, the square error criterion function is:

[0029]

[0030] Where M is the output result of the square error criterion function; n is the number of samples of the target training data; y i The actual value of the i-th sample; is the predicted value of the i-th sample;

[0031] The target condition is that the output result M of the square error criterion function is less than a preset threshold.

[0032] Optionally, maintenance plan data corresponding to each medical waste treatment device is generated based on the fault diagnosis result data and historical maintenance data, including:

[0033] Generate the latest maintenance data of the current medical waste treatment equipment based on the fault diagnosis result data;

[0034] Generate maintenance plan data based on the latest maintenance data, historical maintenance data and current maintenance time of the current medical waste treatment equipment.

[0035] An embodiment of the present invention further provides a device for processing operation data of medical waste treatment equipment, comprising:

[0036] A data acquisition module is used to obtain the current operating data of multiple medical waste treatment equipment;

[0037] A data processing module, used for preprocessing the current operation data to generate multiple groups of statistical indicator data;

[0038] A fault diagnosis module, used for inputting each set of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generating fault diagnosis result data corresponding to each set of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model according to historical maintenance data;

[0039] The maintenance module is used to generate maintenance plan data corresponding to each medical waste treatment equipment based on fault diagnosis result data and historical maintenance data, and to perform visual output display.

[0040] An embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the above-mentioned sewage treatment method is executed.

[0041] An embodiment of the present invention further provides a computer-readable storage medium, comprising: storing instructions, which, when executed on a computer, enable the computer to execute the above-mentioned sewage treatment method.

[0042] The above solution of the present invention includes at least the following beneficial effects:

[0043] The method for processing the operation data of medical waste treatment equipment of the present invention obtains the current operation data of multiple medical waste treatment equipment; pre-processes the current operation data to generate multiple groups of statistical indicator data; inputs each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generates fault diagnosis result data corresponding to each group of statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model according to historical maintenance data; generates maintenance plan data corresponding to each medical waste treatment equipment according to the fault diagnosis result data and historical maintenance data, and performs visual output display. Remote monitoring of medical waste treatment equipment and rapid diagnosis and maintenance management after equipment failure are realized, thereby improving the operation efficiency of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for processing operation data of medical waste treatment equipment of the present invention;

[0045] Figure 2 It is a structural schematic diagram of a device for processing operation data of medical waste treatment equipment of the present invention. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0047] like Figure 1 As shown, an embodiment of the present invention provides a method for processing operation data of medical waste treatment equipment, comprising:

[0048] Step 11, obtaining current operation data of multiple medical waste treatment equipment;

[0049] Step 12, preprocessing the current operation data to generate multiple groups of statistical indicator data;

[0050] Step 13, inputting each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generating fault diagnosis result data corresponding to each group of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model based on historical maintenance data training;

[0051] Step 14, based on the fault diagnosis result data and historical maintenance data, generate maintenance plan data corresponding to each medical waste treatment equipment, and perform visual output display.

[0052] In this embodiment, step 11 can specifically be to acquire data through multiple sensors set on the medical waste treatment equipment; collect data once every minute; the operation data includes: equipment number, equipment number, operation time, operation status, temperature of the sterilization chamber during operation, pressure value inside the medical waste treatment equipment, current position of the medical waste treatment equipment, weight of medical waste treated by the medical waste treatment equipment, average value, maximum value, minimum value and standard deviation of the amount of medical waste treated by the medical waste treatment equipment per minute; wherein, equipment number: unique identification of each equipment; operation time: record the operation time of the equipment; operation status: record the current working status of the equipment; temperature of the sterilization chamber: record the temperature change during the operation of the equipment; pressure: monitor the pressure value inside the equipment; position: locate the area where the equipment is located; output: record the weight of medical waste treated by the equipment;

[0053] The method for processing the operation data of medical waste treatment equipment described in the present invention is used to improve the operation efficiency and customer service quality of medical waste treatment equipment, and can be used for the monitoring system of medical waste treatment equipment, that is, a device for processing the operation data of medical waste treatment equipment, which mainly monitors the operation status, temperature, pressure, weight, current and position and other parameters of the equipment in real time through data acquisition, and transmits the data to the data processing module for analysis and processing, and then remotely transmits the processed data to the cloud management platform, so that maintenance operators can view the data parameters of the on-site equipment and receive fault alarm information in real time on the user interface; the method for processing the operation data of medical waste treatment equipment described in the present invention solves the problems of low maintenance efficiency, easy data loss and errors, untimely equipment maintenance and low fault handling efficiency of existing medical waste treatment equipment during maintenance; remote monitoring of medical waste treatment equipment, rapid diagnosis and maintenance management after equipment failure and intelligent management of on-site medical waste treatment equipment are realized, ensuring the safe and efficient operation of the equipment, thereby improving the operation efficiency of the equipment.

[0054] In an optional embodiment of the present invention, step 12 may include:

[0055] Step 121, cleaning all the current running data, removing abnormal values, duplicate values, and missing values, to obtain a plurality of first pre-processed data;

[0056] Step 122, performing format conversion processing on the first preprocessed data to obtain second preprocessed data;

[0057] Step 123, integrating the second pre-processed data to generate multiple groups of statistical indicator data.

[0058] In this embodiment, step 121 is used to ensure the accuracy and integrity of the data, which may specifically include: noise removal: filtering the sensor data to remove outliers; missing value processing: filling missing values ​​using interpolation, mean filling and other methods; data standardization: standardizing data such as temperature and pressure to facilitate subsequent modeling; data conversion: converting data collected by different sensors into a standard format to facilitate data analysis and processing;

[0059] Step 123 specifically reclassifies the processed second pre-processed data according to the operating data of the medical waste treatment equipment to form a complete operating data of the medical waste treatment equipment; wherein each group of statistical indicator data includes: equipment number, equipment number, operating time, operating status, temperature of the sterilization chamber during operation, pressure value inside the medical waste treatment equipment, current position of the medical waste treatment equipment, weight of medical waste treated by the medical waste treatment equipment, average value, maximum value, minimum value and standard deviation of the amount of medical waste treated by the medical waste treatment equipment per minute.

[0060] In an optional embodiment of the present invention, the process of training a preset neural network model according to historical maintenance data training includes:

[0061] Step 131, extract features from the historical maintenance data to obtain multiple groups of initial training data; specifically, this step may include: Step 1311, extract features from the historical maintenance data according to statistical indicator data to obtain first feature data; Step 1312, extract features from the fault cause data in the historical maintenance data to obtain second feature data; Step 1313, associate the first feature data with the second feature data to obtain initial training data. In this embodiment, the initial training data includes a training set and a test set (for example, 70% for training and 30% for testing), and the first feature data includes: statistical indicators, equipment number, fault type, number of fault occurrences, and maintenance time; the fault cause data (second feature data) includes the fault type, fault location, and fault cause; for example, a temperature type fault, a temperature sensor caused by excessive current; a current type fault, a current type fault caused by excessive current and an overloaded motor; the first feature data and the second feature data are associated to obtain initial training data, that is, the first feature data and the second feature data are associated according to the equipment number to form a complete initial training data;

[0062] Step 132, obtaining the operation status data of the medical waste treatment equipment; wherein the operation status data of the medical waste treatment equipment includes: normal operation status and abnormal operation status;

[0063] Step 133, associating the multiple groups of initial training data with the medical waste treatment equipment operation status data to obtain target training data;

[0064] Step 1331, determining range values ​​corresponding to normal operation state and abnormal operation state of the medical waste treatment equipment according to the extreme operation range of the medical waste treatment equipment;

[0065] Step 1332, comparing the value of each data in each set of initial training data with the range values ​​corresponding to the normal operating state and the abnormal operating state, respectively, determining the corresponding operating state of each set of initial training data, and associating the current initial training data with the operating state data of the medical waste treatment equipment to obtain target training data;

[0066] Specifically, taking the example that each set of data in the initial training data includes equipment number, fault type, number of fault occurrences, maintenance time, fault location and fault cause, first obtain specific initial training data, as shown in Table 1 Initial Training Data Table, and then obtain equipment operation status data, each set of data includes equipment number, operation time, operation status, temperature, pressure, etc., as shown in Table 2 Equipment Operation Status Data Table;

[0067] Table 1, initial training data table

[0068]

[0069] Table 2, Equipment operation status data table

[0070] Equipment No. Run time Running status temperature pressure Load current Handling weight Device 001 1200 normal 135 0.2 10 150 Device 002 800 abnormal 135 0.2 12 200

[0071] The specific associating steps of associating the multiple sets of initial training data with the operating status data of the medical waste treatment equipment may include:

[0072] First, confirm the data structure. Before associating the data, ensure that the structures of the two data sets are clear. The two data sets need to be associated by device number.

[0073] Then determine the association logic, use the device number as the key field, merge the initial training data with the device operating status data, so that the fault information of each device can be combined with its current operating status for subsequent analysis and model training, and use the Pandas library to associate data to generate target training data; the target training data includes statistical indicators, fault type, fault location, fault cause and the current status of the device; after the preset fault diagnosis model is formed, when it is used, the statistical indicators are used as input data, and the model can output the corresponding fault diagnosis result data, and the fault diagnosis result data includes: fault type, fault location, fault cause and the current status of the device.

[0074] Step 134 , training the preset neural network model using the target training data to obtain a preset fault diagnosis model.

[0075] In an optional embodiment of the present invention, in step 134, training a preset neural network model using target training data to obtain a preset fault diagnosis model includes:

[0076] Step 1341, inputting the target training data into the input layer of the preset neural network model for processing to obtain the first layer output;

[0077] Step 1342, inputting the first layer output and the first layer weight into the hidden layer of the preset neural network model for processing to obtain the second layer output;

[0078] Step 1343, inputting the second layer output and the second layer weight into the output layer of the preset neural network model for processing to obtain the third layer output;

[0079] Step 1344, adjusting the first layer weights and the second layer weights according to the third layer output until the square error criterion function corresponding to the third layer meets the target condition, thereby obtaining the preset fault diagnosis model.

[0080] Among them, the square error criterion function is:

[0081] Where M is the output result of the square error criterion function; n is the number of samples of the target training data; y i The actual value of the i-th sample; is the predicted value of the i-th sample;

[0082] The target condition is that the output result M of the square error criterion function is less than a preset threshold.

[0083] In this embodiment, the number of nodes in the input layer is the same as the dimension of the input features. For example, if each sample has 10 features, the input layer will contain 10 nodes. Before the input data is passed into the input layer, the data is usually preprocessed to improve the training effect of the model. For example, the data is converted into a distribution with a mean of 0 and a standard deviation of 1. The data is scaled to a specific range (such as between 0 and 1). These are all helpful to improve the convergence speed of training and the stability of the model. The input data is usually provided in the form of a two-dimensional array, and the data is (number of samples, number of features). For example, if there are 1000 samples and each sample has 10 features, the shape of the input data is (1000, 10). The input layer passes the input data to each node of the first hidden layer, and each node performs a weighted sum calculation on the input data. The weighted sum is nonlinearly transformed through an activation function to obtain the output of the first layer. Common activation functions include ReLU, Sigmoid, and Tanh.

[0084] In this embodiment, the hidden layer is a layer located between the input layer and the output layer, and is responsible for further processing and feature extraction of the input data. The hidden layer receives the output data from the previous layer (i.e., the input layer or the previous hidden layer). Each neuron in the hidden layer performs a weighted sum calculation on the input data, and then performs a nonlinear transformation on the weighted sum through an activation function to obtain the output of the second layer.

[0085] In this embodiment, the output layer receives output data from the last hidden layer, each neuron in the output layer performs weighted sum calculation on the input data, and then the output layer generates a final output through an activation function, and the activation function is a Softmax activation function.

[0086] In an optional embodiment of the present invention, in step 14, the maintenance plan data corresponding to each medical waste treatment device is generated according to the fault diagnosis result data and the historical maintenance data, including:

[0087] Step 141, generating the latest maintenance data of the current medical waste treatment equipment according to the fault diagnosis result data;

[0088] Step 142, generating maintenance plan data according to the latest maintenance data, historical maintenance data and current maintenance time of the current medical waste treatment equipment.

[0089] In this embodiment, maintenance plan data corresponding to each medical waste treatment equipment is generated based on the fault diagnosis result data and the historical maintenance data. Specifically, the current medical waste treatment equipment is repaired according to the fault diagnosis result data to determine the latest maintenance data; then, a risk assessment of the current equipment is performed based on the latest maintenance data, historical maintenance data and current maintenance time of the current medical waste treatment equipment, and maintenance plan data is generated based on the risk assessment; for example, when the historical maintenance data is: the equipment has had 2 motor failures in the past 1000 hours, and each maintenance time is about 24 hours; fault diagnosis result data: the load current exceeds the normal range and the motor fails; maintenance suggestion: replace the motor; equipment status assessment: the equipment is in normal condition; risk assessment: the equipment failure frequency is low and the maintenance time required is short; maintenance plan data: it is recommended to perform routine maintenance once every 1000 hours.

[0090] The following is a specific implementation example to illustrate the specific implementation of the above method:

[0091] Firstly, data is acquired through a plurality of sensors arranged on the medical waste treatment equipment, and data is collected once every minute;

[0092] Data types collected: Equipment number: unique identification of each equipment; Running time: record equipment running time; Running status: record equipment current working status; Load current: record equipment motor current; Temperature: record equipment internal temperature; Pressure: record equipment internal pressure; Location: specific location of equipment; Processing volume: record the amount of medical waste processed by the equipment; Collection frequency: collect data once every minute;

[0093] Data preprocessing: Data cleaning: Clean the collected data to remove outliers, duplicate values, missing values, etc. to ensure the accuracy and completeness of the data; Data conversion: Convert the data collected by different sensors into a standard format to facilitate data analysis and processing; Data integration: Reclassify the processed second preprocessing data according to the operating data of the medical waste treatment equipment to form a complete operating data of the medical waste treatment equipment; Among them, each group of statistical indicator data includes: equipment number, equipment number, operating time, operating status, temperature of the sterilization chamber during operation, pressure value inside the medical waste treatment equipment, current position of the medical waste treatment equipment, weight of medical waste treated by the medical waste treatment equipment, average, maximum, minimum and standard deviation of the amount of medical waste treated by the medical waste treatment equipment per minute.

[0094] Build a preset fault diagnosis model:

[0095] Input each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generate fault diagnosis result data corresponding to each group of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model based on historical maintenance data;

[0096] Fault diagnosis: inputting each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, generating fault diagnosis result data corresponding to each group of statistical indicator data, the fault diagnosis result including fault type, fault location, fault cause, etc.;

[0097] Visual output display:

[0098] Output and display the fault diagnosis result data, and generate the maintenance plan data corresponding to each medical waste treatment equipment based on the fault diagnosis result data and historical maintenance data, and display it visually; maintenance plan data, including maintenance plan, maintenance time, maintenance personnel, etc.;

[0099] Specific example: Current equipment: 200L mobile medical waste treatment machine; Input data: Equipment name: ID37 equipment; Operating status: Idle; Operating time: 500 hours; Load current: 12 mA (normal range: 8-10 mA); Temperature: 135 degrees (normal range: 130-136 degrees); Pressure: 0.2 MPa, (normal range: 0.2 to 0.3 MPa); Processing capacity: 1000 kg; Historical data: The equipment has had 2 motor failures in the past 1000 hours, and each maintenance time is about 24 hours; Fault diagnosis results: The load current exceeds the normal range and the motor fails; Visual output display: Diagnosis result: The motor fails; Maintenance suggestion: Replace the motor; Maintenance plan: It is recommended to perform routine maintenance once every 1000 hours.

[0100] The method for processing the operation data of medical waste treatment equipment of the present invention can be applied to the operation and maintenance management service system of medical waste treatment equipment manufacturers, and has the advantages of reasonable structure, convenient operation, stable data transmission, etc. Through real-time monitoring, data analysis, remote management and customer service and other functions, it realizes the comprehensive operation and maintenance management of medical waste treatment equipment, while improving the operation efficiency and safety of the equipment, and also improving the customer's usage experience and satisfaction, and has broad application prospects.

[0101] like Figure 2 As shown, the embodiment of the present invention further provides a device 20 for processing operation data of medical waste treatment equipment, comprising:

[0102] The data acquisition module 21 is used to obtain the current operation data of multiple medical waste treatment equipment;

[0103] The data processing module 22 is used to pre-process the current operation data to generate multiple sets of statistical indicator data;

[0104] A fault diagnosis module 23 is used to input each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generate fault diagnosis result data corresponding to each group of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model according to historical maintenance data;

[0105] The maintenance module 24 is used to generate maintenance plan data corresponding to each medical waste treatment equipment based on the fault diagnosis result data and historical maintenance data, and perform visual output display.

[0106] In this embodiment, the processing device for the operation data of the medical waste treatment equipment also includes a customer service module, which is used to provide functions such as fault reporting, maintenance appointments and customer feedback to improve customer satisfaction; the processing device also includes a repair and maintenance module that specifically manages the maintenance process of the equipment, including maintenance records, maintenance plan generation and fault analysis suggestions, to ensure timely repair and maintenance of the equipment; the processing device for the operation data of the medical waste treatment equipment described in this embodiment can realize remote monitoring, maintenance and management of the equipment, perform fault diagnosis and maintenance management, thereby improving the operating efficiency of the equipment and customer satisfaction.

[0107] Optionally, the current operation data is preprocessed to generate multiple sets of statistical indicator data, including:

[0108] Clean all the current running data, remove outliers, duplicate values, and missing values, and obtain a plurality of first pre-processed data;

[0109] Performing format conversion processing on the first preprocessed data to obtain second preprocessed data;

[0110] The second pre-processed data is integrated to generate multiple groups of statistical indicator data.

[0111] Optionally, the process of training a preset neural network model based on historical maintenance data includes:

[0112] Extracting features from the historical maintenance data to obtain multiple groups of initial training data;

[0113] Obtain the operating status data of medical waste treatment equipment;

[0114] Associating multiple groups of initial training data with the operating status data of medical waste treatment equipment to obtain target training data;

[0115] The preset neural network model is trained with target training data to obtain a preset fault diagnosis model.

[0116] Optionally, feature extraction is performed on the historical maintenance data to obtain multiple groups of initial training data, including:

[0117] Perform feature extraction processing on the historical maintenance data according to the statistical indicator data to obtain first feature data;

[0118] Performing feature extraction processing on the fault cause data in the historical maintenance data to obtain second feature data;

[0119] The first feature data and the second feature data are associated to obtain initial training data.

[0120] Optionally, a preset neural network model is trained using target training data to obtain a preset fault diagnosis model, including:

[0121] Input the target training data into the input layer of the preset neural network model for processing to obtain the first layer output;

[0122] According to the first layer output and the first layer weight, the hidden layer of the preset neural network model is input for processing to obtain the second layer output;

[0123] According to the second layer output and the second layer weight, input the output layer of the preset neural network model for processing to obtain the third layer output;

[0124] The first layer weights and the second layer weights are adjusted according to the third layer output until the square error criterion function corresponding to the third layer meets the target condition, thereby obtaining the preset fault diagnosis model.

[0125] Optionally, the square error criterion function is:

[0126]

[0127] Where M is the output result of the square error criterion function; n is the number of samples of the target training data; y i The actual value of the i-th sample; is the predicted value of the i-th sample;

[0128] The target condition is that the output result M of the square error criterion function is less than a preset threshold.

[0129] Optionally, maintenance plan data corresponding to each medical waste treatment device is generated based on the fault diagnosis result data and historical maintenance data, including:

[0130] Generate the latest maintenance data of the current medical waste treatment equipment based on the fault diagnosis result data;

[0131] Generate maintenance plan data based on the latest maintenance data, historical maintenance data and current maintenance time of the current medical waste treatment equipment.

[0132] It should be noted that the device is a device corresponding to the above-mentioned method, and all implementation methods in the above-mentioned method are applicable to the embodiments of the device and can achieve the same technical effects.

[0133] The embodiment of the present invention further provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program executes the above method when executed by the processor. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0134] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0135] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0137] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 devices or units, which can be electrical, mechanical or other forms.

[0138] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in each embodiment of the present invention 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.

[0140] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0141] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0142] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0143] The above is a preferred embodiment of the present invention. 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 invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing operation data of medical waste treatment equipment, characterized in that: include: Obtain current operating data of multiple medical waste treatment equipment; Preprocessing the current operation data to generate multiple groups of statistical indicator data; Input each group of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generate fault diagnosis result data corresponding to each group of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model based on historical maintenance data; Based on the fault diagnosis result data and historical maintenance data, the maintenance plan data corresponding to each medical waste treatment equipment is generated and displayed visually.

2. The method for processing operation data of medical waste treatment equipment according to claim 1, characterized in that: Preprocess the current operation data to generate multiple sets of statistical indicator data, including: Clean all the current running data, remove outliers, duplicate values, and missing values, and obtain a plurality of first pre-processed data; Performing format conversion processing on the first preprocessed data to obtain second preprocessed data; The second pre-processed data is integrated to generate multiple groups of statistical indicator data.

3. The method for processing operation data of medical waste treatment equipment according to claim 1, characterized in that: The process of training the preset neural network model based on historical maintenance data includes: Extracting features from the historical maintenance data to obtain multiple groups of initial training data; Obtain the operating status data of medical waste treatment equipment; Associating multiple groups of initial training data with the operating status data of medical waste treatment equipment to obtain target training data; The preset neural network model is trained with target training data to obtain a preset fault diagnosis model.

4. The method for processing operation data of medical waste treatment equipment according to claim 3, characterized in that: Feature extraction is performed on the historical maintenance data to obtain multiple groups of initial training data, including: Perform feature extraction processing on the historical maintenance data according to the statistical indicator data to obtain first feature data; Performing feature extraction processing on the fault cause data in the historical maintenance data to obtain second feature data; The first feature data and the second feature data are associated to obtain initial training data.

5. The method for processing operation data of medical waste treatment equipment according to claim 3, characterized in that: The preset neural network model is trained by target training data to obtain a preset fault diagnosis model, including: Input the target training data into the input layer of the preset neural network model for processing to obtain the first layer output; According to the first layer output and the first layer weight, the hidden layer of the preset neural network model is input for processing to obtain the second layer output; According to the second layer output and the second layer weight, input the output layer of the preset neural network model for processing to obtain the third layer output; The first layer weights and the second layer weights are adjusted according to the third layer output until the square error criterion function corresponding to the third layer meets the target condition, thereby obtaining the preset fault diagnosis model.

6. The method for processing operation data of medical waste treatment equipment according to claim 5, characterized in that: The square error criterion function is: Where M is the output result of the square error criterion function; n is the number of samples of the target training data; y i The actual value of the i-th sample; is the predicted value of the i-th sample; The target condition is that the output result M of the square error criterion function is less than a preset threshold.

7. The method for processing operation data of medical waste treatment equipment according to claim 1, characterized in that: Based on the fault diagnosis result data and historical maintenance data, the maintenance plan data corresponding to each medical waste treatment equipment is generated, including: Generate the latest maintenance data of the current medical waste treatment equipment based on the fault diagnosis result data; Generate maintenance plan data based on the latest maintenance data, historical maintenance data and current maintenance time of the current medical waste treatment equipment.

8. A device for processing operation data of medical waste treatment equipment, characterized in that: include: A data acquisition module is used to obtain current operating data of multiple medical waste treatment equipment; A data processing module, used for preprocessing the current operation data to generate multiple groups of statistical indicator data; A fault diagnosis module, used for inputting each set of the statistical indicator data into a preset fault diagnosis model for fault diagnosis, and generating fault diagnosis result data corresponding to each set of the statistical indicator data; wherein the preset fault diagnosis model is obtained by training a preset neural network model according to historical maintenance data; The maintenance module is used to generate maintenance plan data corresponding to each medical waste treatment equipment based on fault diagnosis result data and historical maintenance data, and to perform visual output display.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images