Abnormal state monitoring method and system for medical sterilizer

Abstract

The invention discloses an abnormal state monitoring method and system for a medical sterilizer, and the method comprises the steps: S1, collecting and preprocessing the temperature and pressure data of the medical sterilizer, and obtaining the preprocessed temperature and pressure data; s2, performing time window division on the preprocessed temperature and pressure data, arranging the preprocessed temperature and pressure data into a temperature and pressure two-dimensional matrix, and calculating temperature and pressure feature vectors; s3, calculating the difference variation of the temperature and pressure data, identifying inflection point moments, carrying out time sequence division on the preprocessed temperature and pressure data according to three time stages of heating, constant temperature and cooling, and then extracting background vectors of all the stages; s4, background feature elimination is carried out on the temperature feature vector and the pressure feature vector, and an alarm feature vector is obtained; and S5, calculating the abnormal probability of the medical sterilizer according to the alarm feature vector, classifying alarm reasons, and outputting inspection suggestions. The problem that the monitoring effect is poor due to the fact that a temperature change stage is not considered in monitoring of a traditional medical sterilizer can be solved.

Description

Technical Field

[0001] The present invention relates to the field of medical sterilizers, and in particular to an abnormal state monitoring method and system for a medical sterilizer. Background Art

[0002] Medical sterilizers are an indispensable part of medical equipment. Their main function is to kill or remove microorganisms on medical devices, dressings, surgical supplies, etc. through high temperature, high pressure or chemical methods to ensure the safety and sterility of the medical process. However, during the operation of medical sterilizers, abnormal conditions may occur due to various reasons, such as abnormal temperature and pressure control. These abnormal conditions may not only lead to poor sterilization effects, but may also cause damage to the sterilizer itself and even cause safety accidents.

[0003] Traditional methods for detecting abnormal conditions of medical sterilizers mainly rely on manual inspections and threshold alarm systems. Manual inspections usually detect potential problems by regularly checking the sterilizer's operating records and equipment status, but this method has problems such as poor timeliness and high labor costs; the threshold alarm system sets fixed temperature and pressure thresholds, and triggers alarms when the actual values ​​exceed or fall below these thresholds; however, this method has the following shortcomings:

[0004] First, it is difficult for traditional methods to issue alarms in combination with the temperature change stage, and it is impossible to make dynamic adjustments according to the different working stages of the sterilizer (such as the heating stage, constant temperature stage, and cooling stage). For example, in the heating stage, a rapid increase in temperature is normal, but in the constant temperature stage, if the temperature still rises rapidly, it may indicate that the sterilizer has a fault and an alarm needs to be issued immediately.

[0005] Secondly, traditional methods cannot achieve joint monitoring of temperature and pressure. The normal operation of medical sterilizers requires the synergy between temperature and pressure. In some cases, the temperature rises but the pressure remains unchanged, or the pressure rises but the temperature does not change accordingly. These may indicate that the sterilizer is in an abnormal state. However, traditional detection methods usually only focus on the changes in a single parameter and ignore the correlation between parameters, so they cannot accurately identify this joint abnormality. Summary of the invention

[0006] In view of this, the present invention aims to provide a method and system for monitoring the abnormal state of a medical sterilizer, aiming to solve the problem that the traditional abnormal monitoring method of a medical sterilizer is difficult to combine the temperature change stage for alarm, and the abnormal monitoring effect is poor due to the inability to achieve joint monitoring of temperature and pressure.

[0007] A method for monitoring abnormal state of a medical sterilizer comprises the following steps:

[0008] S1: collect temperature and pressure data of the medical sterilizer and perform preprocessing to obtain preprocessed temperature and pressure data;

[0009] S2: Divide the preprocessed temperature and pressure data into time windows and arrange them into two-dimensional temperature and pressure matrices to calculate the temperature and pressure eigenvectors;

[0010] S3: Calculate the difference change of temperature and pressure data, identify the inflection point, and divide the pre-processed temperature and pressure data into three time stages: heating, constant temperature and cooling, and then extract the background vector of each stage;

[0011] S4: Eliminate the background features of the temperature and pressure feature vectors to obtain an alarm feature vector;

[0012] S5: Calculate the abnormal probability of the medical sterilizer based on the alarm feature vector, classify the alarm causes, and output inspection opinions.

[0013] Furthermore, the step S1 collects the temperature and pressure data of the medical sterilizer and performs preprocessing to obtain the preprocessed temperature and pressure data, including:

[0014] S11: Acquire temperature and pressure data of the medical sterilizer, wherein the temperature and pressure data are time series data in seconds;

[0015] S12: The temperature and pressure data of the medical sterilizer were subjected to the 3σ principle to eliminate outliers, and then the missing values ​​were filled using the mean value method to obtain the preliminary data of the medical sterilizer;

[0016] S13: The preliminary data of the medical sterilizer were standardized using the Z-score method to obtain the pre-processed temperature and pressure data.

[0017] Furthermore, the step S2 divides the preprocessed temperature and pressure data into time windows and arranges them into a temperature and pressure two-dimensional matrix to calculate the temperature and pressure feature vectors, including:

[0018] S21: Divide the preprocessed temperature and pressure data into time windows of 30 seconds to obtain data segments within each time window;

[0019] Dividing data into 30-second time windows can ensure that the data segments in each time window contain enough information to reflect the working status of the sterilizer, while avoiding processing difficulties caused by data being too sparse or too dense. In addition, the 30-second time window is short enough to detect and handle abnormal situations in a timely manner, ensuring the immediate responsiveness of the monitoring system. At the same time, since the subsequent feature extraction is based on neural networks, it can also pay attention to the changing trend of data within 30 seconds, avoiding the problem of false alarms caused by abnormal single data points.

[0020] S22: for each data segment in each time window, the preprocessed temperature and pressure data are arranged into a temperature and pressure two-dimensional matrix; each row of the temperature and pressure two-dimensional matrix represents the temperature and pressure value at a time point; such a processing method unifies the temperature and pressure data in time and space, and facilitates the subsequent characteristic vector calculation and joint monitoring;

[0021] S23: Calculate the temperature and pressure characteristic vectors. The calculation method is:

[0022] First, define the temperature sequence T = [t1, t2, ..., t n ], pressure sequence P = [p1, p2, ..., p n ], where [t1, t2, ..., t n ] is the preprocessed temperature data from the first moment to the nth moment, n is the number of moments, [p1, p2, ..., p n ] is the preprocessed pressure data from the first moment to the nth moment;

[0023]

[0024]

[0025] in, are the hidden states of the temperature data from the first moment to the nth moment output by the gated recurrent unit network, GRU() is the gated recurrent unit network operation, They are the hidden states of the pressure data from the first moment to the nth moment output by the gated recurrent unit network;

[0026] Secondly, Concatenate into temperature hidden state sequence Will Splicing into a pressure hidden state sequence

[0027] Finally, the temperature hidden state sequence, temperature sequence, pressure sequence, and pressure hidden state sequence are concatenated in sequence to obtain the temperature and pressure four-dimensional matrix, and then input into the convolutional neural network with a convolution kernel size of 4 to obtain the temperature and pressure fusion vector. The calculation method is:

[0028]

[0029] Among them, F fusion is the temperature and pressure fusion vector, CNN( ) is the convolutional neural network operation with a convolution kernel size of 4;

[0030] The temperature and pressure fusion vector, the hidden state of the temperature data at the nth moment, and the hidden state of the pressure data at the nth moment are fused to obtain the temperature and pressure feature vectors. The calculation method is:

[0031]

[0032] Where F is the temperature and pressure feature vector, MLP ( ) is the multi-layer perceptron operation;

[0033] Step S23 first uses the GRU network as a feature enhancement method to process the temperature and pressure data, capture the long-term dependencies in the data, and obtain their respective hidden state sequences; then, the obtained hidden state sequence is concatenated with the original data into a four-dimensional matrix and input into the convolutional neural network for feature fusion;

[0034] The convolutional neural network uses a convolution kernel of dimension 4, which matches the dimension of the matrix exactly, and can simultaneously focus on the temperature hidden state, temperature, pressure, and pressure hidden state; because the hidden state sequence contains temporal dependency information, the convolutional neural network has actually incorporated the previous context information when extracting local features. This makes the extracted features not only local but also temporal; because the GRU network can retain historical information, even if there are individual outliers in the input data, the system can correct or ignore them through context information, thereby enhancing the robustness of the system.

[0035] Furthermore, the step S3 calculates the difference variation of the temperature and pressure data, identifies the inflection point, and divides the pre-processed temperature and pressure data into three stages: heating, constant temperature, and cooling, and then extracts the background vector of each stage, including:

[0036] S31: Calculate the temperature and pressure data difference change and identify the inflection point. The calculation method is:

[0037]

[0038]

[0039] Δti =t i+1 -t i

[0040] Δp i =p i+1 -p i

[0041] time=MLP(MLP(Δt i , μ, μ part ), Δp i )

[0042] Where μ is the global standard deviation of temperature, μ part is the local standard deviation of temperature, k is the local length, Δt i is the temperature difference change at the i-th moment, i is the time index, j is the count index, Δp i is the pressure difference change at the i-th moment, and time is the inflection point;

[0043] S32: According to the inflection point, the preprocessed temperature and pressure data are divided into three stages: heating, constant temperature and cooling, and the stage labels are added to obtain temperature and pressure sequences with stage labels, which are represented as T′=[t′1, t′2, ..., t′ n ] and P′=[p′1,p′2,...,p′ n ];

[0044] S33: Construct a gated recurrent unit network with transfer, and extract the background vector of each stage according to the temperature and pressure data with stage labels. The calculation method is:

[0045] B=GRU Q (T′, ΔT, F)

[0046] Among them, B is the background vector of each stage, GRU W () is the gated recurrent unit network operation with transfer;

[0047] Q = GRU(T′, ΔT, P′, AP)

[0048] Among them, Q is the transit sequence, including the position identifier; ΔT is the temperature difference sequence, and AP is the pressure difference sequence;

[0049] The gated recurrent unit network GRU with transition W (), taking the gated recurrent unit network GRU as the network basis, according to the position mark in the transit sequence Q, a transit multilayer perceptron is added at the corresponding position of the gated recurrent unit network, and each transit multilayer perceptron divides the gated recurrent unit network into a segment;

[0050] The structure of the relay multilayer perceptron is the same as that of the traditional multilayer perceptron MLP. The difference is that in terms of data flow, the relay multilayer perceptron connects all gated recurrent units that do not cross paragraphs forward and only connects adjacent gated recurrent units backward;

[0051] The GRU network with transit introduces a transit sequence Q, which contains position identifiers and can clearly indicate the stage of temperature and pressure data, so that the network can consciously pay attention to the stage characteristics of the data when processing data; the transit sequence Q can be regarded as an additional input feature, guiding the GRU network to adopt different processing strategies at different stages. This strategic adjustment helps the network to more accurately capture and utilize the stage characteristics of the data;

[0052] The GRU network with transit adds a transit multilayer perceptron to the corresponding position of the GRU network, dividing the GRU network into multiple sections, each of which focuses on processing the data of one stage; from a mathematical point of view, this division can be regarded as a segmentation of the state space of the GRU network, and the state space of each section focuses on representing the data features of a specific stage, thereby avoiding mutual interference between the data features of different stages;

[0053] The relay multi-layer perceptron has a special design for data flow. It connects all gated recurrent units that do not cross paragraphs forward and only connects adjacent gated recurrent units backward, so that the network can maintain smooth information transmission when processing data, while avoiding unnecessary cross-stage information transmission;

[0054] Compared with the traditional GRU network that processes data of all time steps equally without considering the stage characteristics of the data, through the above design, the gated recurrent unit network with transit can more accurately extract the background vector of each stage. The background vector not only contains the data features within the stage, but also implies the transition information between stages, laying a solid foundation for subsequent background feature separation and abnormal state alarm.

[0055] Furthermore, the step S4 eliminates background features of the temperature and pressure feature vectors to obtain an alarm feature vector, including:

[0056] S41: Perform stage identification on the temperature and pressure feature vectors to obtain the temperature and pressure feature vectors with stage labels. The calculation method is:

[0057] F′=MLP(F,t i , p i )

[0058] Among them, F′ is the temperature and pressure feature vector with stage labels;

[0059] S42: Eliminate the background features according to the temperature and pressure feature vectors with stage labels to obtain the alarm feature vector. The calculation method is:

[0060] f=W3·MLP (W1·F′, W2·B, (W1·F′-W2·B))

[0061] Among them, f is the alarm feature vector, W3 is the dimension reduction matrix, W1 and W2 are the first dimension increase matrix and the second dimension increase matrix respectively;

[0062] W1 and W2 are used as dimension-raising matrices. First, F′ and background vector B are mapped to a higher-dimensional space to better capture the complex relationship between them. Then, by calculating W1·F′-W2·B, the difference between the feature vector and the background vector is obtained, highlighting the features related to the abnormal state. Finally, the multi-layer perceptron and the dimension-reducing matrix W3 are used to map the processed feature vector back to the low-dimensional space to obtain the alarm feature vector, which effectively eliminates the background information irrelevant to the abnormal state and improves the accuracy of abnormal monitoring.

[0063] Among them, the dimension increase operation enables the feature vector to be expanded in a higher-dimensional space, thereby capturing more detailed information. The dimension reduction operation retains the most important features, removes redundant information, and makes the alarm feature vector more compact;

[0064] Due to the existence of the background feature elimination step, the present invention has stronger robustness against noise and interference; in practical applications, the temperature and pressure data of the medical sterilizer may be affected by various factors, such as equipment aging, environmental changes, etc., resulting in noise and interference in the data; through background feature elimination, the present invention can effectively suppress these noise and interference and improve the robustness of abnormal monitoring.

[0065] Furthermore, the step S5 calculates the abnormal probability of the medical sterilizer according to the alarm feature vector, classifies the alarm causes, and outputs inspection opinions, including:

[0066] S51: Calculate the abnormal probability of the medical sterilizer according to the alarm feature vector, and the calculation method is:

[0067] pro = sigmoid(MLP(f, t i , p i ))

[0068] Among them, pro is the abnormal probability of medical sterilizer, sigmoid() sigmoid function;

[0069] S52: Decode the alarm result and classify the alarm cause. The calculation method is:

[0070] pro′=softmax(MLP(f,t i , p i ))

[0071] Among them, pro′ is the probability distribution of alarm reasons, and softmax() is the softmax function operation;

[0072] S53: Output inspection opinions based on the alarm cause classification results.

[0073] The present invention also discloses an abnormal state monitoring system for a medical sterilizer, comprising:

[0074] Sterilizer data processing module: collects temperature and pressure data of medical sterilizer and performs preprocessing to obtain preprocessed temperature and pressure data;

[0075] Temperature and pressure feature vector extraction module: divides the preprocessed temperature and pressure data into time windows, arranges them into temperature and pressure two-dimensional matrices, and calculates temperature and pressure feature vectors;

[0076] Background vector extraction module: calculates the difference change of temperature and pressure data, identifies the inflection point, and divides the pre-processed temperature and pressure data into three stages: heating, constant temperature and cooling, and then extracts the background vector of each stage;

[0077] Background feature elimination module: eliminates the background features of temperature and pressure feature vectors to obtain alarm feature vectors;

[0078] Alarm module: Calculate the abnormal probability of the medical sterilizer based on the alarm feature vector, classify the alarm causes, and output inspection opinions.

[0079] The abnormal state monitoring method of the above-mentioned medical sterilizer is realized through this system.

[0080] Compared with the prior art, the advantages of the present invention are:

[0081] (1) The present invention always takes temperature and pressure data as the object of joint monitoring. Whether in the calculation of feature vectors or in the calculation of abnormal probability and the classification of alarm causes, the correlation between temperature and pressure data is fully considered, thereby improving the comprehensiveness and accuracy of abnormal monitoring.

[0082] (2) The present invention calculates the difference change of temperature and pressure data, captures the change of data between adjacent moments, identifies the turning point moment, and divides the pre-processed data into three stages: heating, constant temperature, and cooling; secondly, the present invention eliminates background features of temperature and pressure feature vectors, removes background information irrelevant to the abnormal state, and highlights features related to the abnormal state. It can more accurately extract the alarm feature vector related to the abnormal state, thereby improving the accuracy of abnormal monitoring.

[0083] (2) The present invention constructs a gated recurrent unit network with transit. By introducing a transit sequence Q, the sequence contains a position identifier, which can clearly indicate the stage of the temperature and pressure data, so that the network can consciously pay attention to the stage characteristics of the data when processing the data; in addition, the gated recurrent unit network with transit adds a transit multilayer perceptron at the corresponding position of the gated recurrent unit network, dividing the GRU network into multiple sections, each section focuses on processing the data of one stage, thereby avoiding mutual interference of data features of different stages.

[0084] (3) The present invention proposes adaptive local standard deviation calculation, and adopts a multi-layer perceptron to dynamically generate local length, so that the calculation of local standard deviation has adaptive capability. This design can automatically adjust the size of the local window according to the data characteristics at different times, thereby more accurately reflecting the local change characteristics of the data, improving the accuracy of inflection point recognition, and providing a more reliable data basis for stage division and background vector extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 A schematic diagram of the process of the abnormal state monitoring method of the medical sterilizer provided by the present invention;

[0086] Figure 2 It is a schematic diagram of the process of extracting temperature and pressure characteristic vectors in the method of the present invention;

[0087] Figure 3 Schematic diagram of the network structure of the gated recurrent unit network with transit in the method of the present invention. DETAILED DESCRIPTION

[0088] The present invention is further described below in conjunction with the accompanying drawings, but the present invention is not limited in any way. Any changes or substitutions made based on the teachings of the present invention belong to the protection scope of the present invention.

[0089] Embodiment 1:

[0090] See also Figure 1 , a method for monitoring abnormal state of a medical sterilizer, comprising the following steps:

[0091] S1: collect temperature and pressure data of the medical sterilizer and perform preprocessing to obtain preprocessed temperature and pressure data;

[0092] S11: Acquire temperature and pressure data of the medical sterilizer, wherein the temperature and pressure data are time series data in seconds;

[0093] S12: The temperature and pressure data of the medical sterilizer were subjected to the 3σ principle to eliminate outliers, and then the missing values ​​were filled using the mean value method to obtain the preliminary data of the medical sterilizer;

[0094] S13: The preliminary data of the medical sterilizer were standardized using the Z-score method to obtain the pre-processed temperature and pressure data.

[0095] S2: Divide the preprocessed temperature and pressure data into time windows and arrange them into two-dimensional temperature and pressure matrices to calculate the temperature and pressure eigenvectors. Figure 2 ;

[0096] S21: Divide the preprocessed temperature and pressure data into time windows of 30 seconds to obtain data segments within each time window;

[0097] Dividing data into 30-second time windows can ensure that the data segments in each time window contain enough information to reflect the working status of the sterilizer, while avoiding processing difficulties caused by data being too sparse or too dense. In addition, the 30-second time window is short enough to detect and handle abnormal situations in a timely manner, ensuring the immediate responsiveness of the monitoring system. At the same time, since the subsequent feature extraction is based on neural networks, it can also pay attention to the changing trend of data within 30 seconds, avoiding the problem of false alarms caused by abnormal single data points.

[0098] S22: for each data segment in each time window, the preprocessed temperature and pressure data are arranged into a temperature and pressure two-dimensional matrix; each row of the temperature and pressure two-dimensional matrix represents the temperature and pressure value at a time point; such a processing method unifies the temperature and pressure data in time and space, and facilitates the subsequent characteristic vector calculation and joint monitoring;

[0099] S23: Calculate the temperature and pressure characteristic vectors. The calculation method is:

[0100] First, define the temperature sequence T = [t1, t2, ..., t n ], pressure sequence P = [p1, p2, ..., p n ], where [t1, t2, ..., t n] is the preprocessed temperature data from the first moment to the nth moment, n is the number of moments, [p1, p2, ..., p n ] is the preprocessed pressure data from the first moment to the nth moment;

[0101]

[0102]

[0103] in, are the hidden states of the temperature data from the first moment to the nth moment output by the gated recurrent unit network, GRU() is the gated recurrent unit network operation, They are the hidden states of the pressure data from the first moment to the nth moment output by the gated recurrent unit network;

[0104] Secondly, Concatenate into temperature hidden state sequence Will Splicing into a pressure hidden state sequence

[0105] Finally, the temperature hidden state sequence, temperature sequence, pressure sequence, and pressure hidden state sequence are concatenated in sequence to obtain the temperature and pressure four-dimensional matrix, and then input into the convolutional neural network with a convolution kernel size of 4 to obtain the temperature and pressure fusion vector. The calculation method is:

[0106]

[0107] Among them, F fusion is the temperature and pressure fusion vector, CNN( ) is the convolutional neural network operation with a convolution kernel size of 4;

[0108] The temperature and pressure fusion vector, the hidden state of the temperature data at the nth moment, and the hidden state of the pressure data at the nth moment are fused to obtain the temperature and pressure feature vectors. The calculation method is:

[0109]

[0110] Where F is the temperature and pressure feature vector, MLP() is the multi-layer perceptron operation;

[0111] Step S23 first uses the GRU network as a feature enhancement method to process the temperature and pressure data, capture the long-term dependencies in the data, and obtain their respective hidden state sequences; then, the obtained hidden state sequence is concatenated with the original data into a four-dimensional matrix and input into the convolutional neural network for feature fusion;

[0112] The convolutional neural network uses a convolution kernel of dimension 4, which matches the dimension of the matrix exactly, and can simultaneously focus on the temperature hidden state, temperature, pressure, and pressure hidden state; because the hidden state sequence contains temporal dependency information, the convolutional neural network has actually incorporated the previous context information when extracting local features. This makes the extracted features not only local but also temporal; because the GRU network can retain historical information, even if there are individual outliers in the input data, the system can correct or ignore them through context information, thereby enhancing the robustness of the system.

[0113] S3: Calculate the difference change of temperature and pressure data, identify the inflection point, and divide the pre-processed temperature and pressure data into three time stages: heating, constant temperature and cooling, and then extract the background vector of each stage;

[0114] S31: Calculate the temperature and pressure data difference change and identify the inflection point. The calculation method is:

[0115]

[0116]

[0117] Δt i =t i+1 -t i

[0118] Δp i =p i+1 -p i

[0119] time=MLP(MLP(Δt i , μ, μ part ), Δp i )

[0120] Where μ is the global standard deviation of temperature, μ part is the local standard deviation of temperature, k is the local length, Δt i is the temperature difference change at the i-th moment, i is the time index, j is the count index, Δp i is the pressure difference change at the i-th moment, and time is the inflection point;

[0121] In particular, when the data fluctuates greatly or the accuracy requirement is high, an adaptive local window can be used to replace the fixed local length k. The calculation method is:

[0122] k=MLP(T,i)

[0123] By calculating the difference change of temperature and pressure data, step S31 can accurately capture the change of data between adjacent moments; the local standard deviation is different from the traditional local standard deviation calculated by fixed window size. Here, the local length k is dynamically generated by multi-layer perceptron, so that the calculation of local standard deviation has adaptive ability, so it can automatically adjust the size of local window according to the data characteristics at different moments, so as to more accurately reflect the local change characteristics of data;

[0124] The identification of the inflection point combines the global standard deviation, the local standard deviation and the difference change, not only taking into account the global characteristics of the data, but also taking into full account the local changes of the data, thereby improving the accuracy of identification; if only focusing on local features, such as simply calculating the local extreme points, while ignoring the guidance of global characteristics, it may lead to the extreme points identified being not the true stage demarcation points of temperature changes, thereby causing misjudgment of stage identification in subsequent steps; therefore, in the present invention, the dual attention to global features and local features is indispensable, they complement each other and jointly ensure the accuracy of data processing and stage identification;

[0125] S32: According to the inflection point, the preprocessed temperature and pressure data are divided into three stages: heating, constant temperature and cooling, and the stage labels are added to obtain temperature and pressure sequences with stage labels, which are represented as T′=[t′1, t′2, ..., t′ n ] and P′=[p′1,p′2,...,p′ n ];

[0126] S33: Construct a gated recurrent unit network with transfer, and extract the background vector of each stage according to the temperature and pressure data with stage labels. The calculation method is:

[0127] B=GRU Q (T′, ΔT, F)

[0128] Among them, B is the background vector of each stage, GRU Q ( ) is the gated recurrent unit network operation with transfer;

[0129] Q = GRU(T′, ΔT, P′, ΔP)

[0130] Among them, Q is the transit sequence, including the position identifier; ΔT is the temperature difference sequence, and ΔP is the pressure difference sequence;

[0131] The gated recurrent unit network with transit GRUQ(), see Figure 3, taking the gated recurrent unit network GRU as the network basis, according to the position mark in the transit sequence Q, a transit multilayer perceptron is added at the corresponding position of the gated recurrent unit network, and each transit multilayer perceptron divides the gated recurrent unit network into a segment;

[0132] The structure of the relay multilayer perceptron is the same as that of the traditional multilayer perceptron MLP. The difference is that in terms of data flow, the relay multilayer perceptron connects all gated recurrent units that do not cross paragraphs forward and only connects adjacent gated recurrent units backward;

[0133] The GRU network with transit introduces a transit sequence Q, which contains position identifiers and can clearly indicate the stage of temperature and pressure data, so that the network can consciously pay attention to the stage characteristics of the data when processing data; the transit sequence Q can be regarded as an additional input feature, guiding the GRU network to adopt different processing strategies at different stages. This strategic adjustment helps the network to more accurately capture and utilize the stage characteristics of the data;

[0134] The GRU network with transit adds a transit multilayer perceptron to the corresponding position of the GRU network, dividing the GRU network into multiple sections, each of which focuses on processing the data of one stage; from a mathematical point of view, this division can be regarded as a segmentation of the state space of the GRU network, and the state space of each section focuses on representing the data features of a specific stage, thereby avoiding mutual interference between the data features of different stages;

[0135] The relay multi-layer perceptron has a special design for data flow. It connects all gated recurrent units that do not cross paragraphs forward and only connects adjacent gated recurrent units backward, so that the network can maintain smooth information transmission when processing data, while avoiding unnecessary cross-stage information transmission;

[0136] Compared with the traditional GRU network that processes data of all time steps equally without considering the stage characteristics of the data, through the above design, the gated recurrent unit network with transit can more accurately extract the background vector of each stage. The background vector not only contains the data features within the stage, but also implies the transition information between stages, laying a solid foundation for subsequent background feature separation and abnormal state alarm.

[0137] S4: Eliminate the background features of the temperature and pressure feature vectors to obtain an alarm feature vector;

[0138] S41: Perform stage identification on the temperature and pressure feature vectors to obtain the temperature and pressure feature vectors with stage labels. The calculation method is:

[0139] F′=MLP(F,t i ,pi )

[0140] Among them, F' is the temperature and pressure feature vector with stage labels;

[0141] S42: Eliminate the background features according to the temperature and pressure feature vectors with stage labels to obtain the alarm feature vector. The calculation method is:

[0142] f=W3·MLP(W1·F′,W2·B,(W1·F′-W2·B))

[0143] Among them, f is the alarm feature vector, W3 is the dimension reduction matrix, W1 and W2 are the first dimension increase matrix and the second dimension increase matrix respectively;

[0144] W1 and W2 are used as dimensionality-raising matrices. First, F' and background vector B are mapped to a higher-dimensional space to better capture the complex relationship between them. Then, by calculating W1·F'-W2·B, the difference between the feature vector and the background vector is obtained, highlighting the features related to the abnormal state. Finally, the multi-layer perceptron and the dimensionality reduction matrix W3 are used to map the processed feature vector back to the low-dimensional space to obtain the alarm feature vector, which effectively eliminates the background information irrelevant to the abnormal state and improves the accuracy of abnormality monitoring.

[0145] Among them, the dimension increase operation enables the feature vector to be expanded in a higher-dimensional space, thereby capturing more detailed information. The dimension reduction operation retains the most important features, removes redundant information, and makes the alarm feature vector more compact;

[0146] Due to the existence of the background feature elimination step, the present invention has stronger robustness against noise and interference; in practical applications, the temperature and pressure data of the medical sterilizer may be affected by various factors, such as equipment aging, environmental changes, etc., resulting in noise and interference in the data; through background feature elimination, the present invention can effectively suppress these noise and interference and improve the robustness of abnormal monitoring.

[0147] S5: Calculate the abnormal probability of the medical sterilizer according to the alarm feature vector, classify the alarm causes, and output inspection opinions;

[0148] S51: Calculate the abnormal probability of the medical sterilizer according to the alarm feature vector, and the calculation method is:

[0149] pro = sigmoid(MLP(f, t i , p i ))

[0150] Among them, pro is the abnormal probability of medical sterilizer, sigmoid() sigmoid function;

[0151] When pro>0.6, an alarm is issued;

[0152] When pro≤0.6, no alarm will be given;

[0153] S52: Decode the alarm result and classify the alarm cause. The calculation method is:

[0154] pro′=softmax(MLP(f,t i , p i ))

[0155] Among them, pro′ is the probability distribution of alarm reasons, and softmax() is the softmax function operation;

[0156] S53: Output inspection opinions according to the alarm cause classification results;

[0157] For example, in a certain time window, the temperature and pressure data of the medical sterilizer are collected, and after preprocessing, feature extraction, background feature elimination and other steps, the alarm feature vector f = [0.5, -0.3, 0.2] is obtained. The alarm feature vector f and the current temperature of 120°C and pressure of 2.5atm are input into the MLP network, and pro = 0.69 is obtained, which means that the abnormal probability of the medical sterilizer at the current moment is 0.69>0.6, so an alarm will be issued;

[0158] Next, the same alarm feature vector and temperature pressure are input into another MLP network to calculate the probability distribution pro′ of the alarm cause

[0159] The output of the MLP network is [1.5, -0.5, 0.3] (the output is a vector, each element corresponds to the probability of an abnormal cause), and the output is converted into a probability distribution through the softmax function:

[0160] pro′=softmax([1.5,-0.5,0.3])=[0.659, 0.119, 0.222]

[0161] It means that at the current moment, the possible abnormal causes and probabilities of the medical sterilizer are:

[0162] Cause 1 (heating system failure): 65.9%

[0163] Cause 2 (pressure sensor failure): 11.9%

[0164] Reason 3 (cooling system failure): 22.2%

[0165] Since the heating system has the highest probability of failure, the inspection advice for heating system failure is output:

[0166] Check whether the heating element is damaged, such as whether the resistance wire is broken or the heating tube is damaged;

[0167] Check whether the temperature controller is malfunctioning, such as whether the temperature sensor is accurate and whether the controller circuit is normal;

[0168] If there is a problem with the heating system, please replace the damaged parts or adjust the controller parameters in time to ensure that the temperature can reach the expected value and remain stable.

[0169] Embodiment 2:

[0170] A medical sterilizer abnormal state monitoring system, comprising:

[0171] Sterilizer data processing module: collects temperature and pressure data of medical sterilizer and performs preprocessing to obtain preprocessed temperature and pressure data;

[0172] Temperature and pressure feature vector extraction module: divides the preprocessed temperature and pressure data into time windows, arranges them into temperature and pressure two-dimensional matrices, and calculates temperature and pressure feature vectors;

[0173] Background vector extraction module: calculates the difference change of temperature and pressure data, identifies the inflection point, and divides the pre-processed temperature and pressure data into three stages: heating, constant temperature and cooling, and then extracts the background vector of each stage;

[0174] Background feature elimination module: eliminates the background features of temperature and pressure feature vectors to obtain alarm feature vectors;

[0175] Alarm module: Calculate the abnormal probability of the medical sterilizer based on the alarm feature vector, classify the alarm causes, and output inspection opinions.

[0176] The method in Example 1 is implemented by the abnormal state monitoring system for the medical sterilizer in this embodiment.

[0177] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in multiple embodiments of the present invention.

[0179] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring abnormal state of a medical sterilizer, characterized in that: The following steps are involved: S1: collect temperature and pressure data of the medical sterilizer and perform preprocessing to obtain preprocessed temperature and pressure data; S2: Divide the preprocessed temperature and pressure data into time windows and arrange them into two-dimensional temperature and pressure matrices to calculate the temperature and pressure eigenvectors; S3: Calculate the difference change of temperature and pressure data, identify the inflection point, and divide the pre-processed temperature and pressure data into three time stages: heating, constant temperature and cooling, and then extract the background vector of each stage; S4: Eliminate the background features of the temperature and pressure feature vectors to obtain an alarm feature vector; S5: Calculate the abnormal probability of the medical sterilizer based on the alarm feature vector, classify the alarm causes, and output inspection opinions.

2. The abnormal state monitoring method of a medical sterilizer according to claim 1, characterized in that: The S1 step includes: S11: Acquire temperature and pressure data of a medical sterilizer, the temperature and pressure data; S12: The temperature and pressure data of the medical sterilizer were subjected to the 3σ principle to eliminate outliers, and then the missing values ​​were filled using the mean value method to obtain the preliminary data of the medical sterilizer; S13: The preliminary data of the medical sterilizer were standardized using the Z-score method to obtain the pre-processed temperature and pressure data.

3. The abnormal state monitoring method of a medical sterilizer according to claim 2, characterized in that: The S2 step includes: S21: Divide the preprocessed temperature and pressure data into time windows of 30 seconds to obtain data segments within each time window; S22: for each data segment in the time window, arranging the preprocessed temperature and pressure data into a temperature and pressure two-dimensional matrix; each row of the temperature and pressure two-dimensional matrix represents the temperature and pressure value at a time point; S23: Calculate the temperature and pressure characteristic vectors. The calculation method is: First, define the temperature sequence T = [t1, t2, ..., t n ], pressure sequence P = [p1, p2, ..., p n ], where [t1,t2,…,t n ] is the preprocessed temperature data from the first moment to the nth moment, n is the number of moments, [p1,p2,…,p n ] is the preprocessed pressure data from the first moment to the nth moment; in, are the hidden states of the temperature data from the first moment to the nth moment output by the gated recurrent unit network, GRU() is the gated recurrent unit network operation, They are the hidden states of the pressure data from the first moment to the nth moment output by the gated recurrent unit network; Secondly, Concatenate into temperature hidden state sequence Will Splicing into a pressure hidden state sequence Finally, the temperature hidden state sequence, temperature sequence, pressure sequence, and pressure hidden state sequence are concatenated in sequence to obtain the temperature and pressure four-dimensional matrix, and then input into the convolutional neural network with a convolution kernel size of 4 to obtain the temperature and pressure fusion vector. The calculation method is: Among them, F fusion is the temperature and pressure fusion vector, CNN() is the convolutional neural network operation with a convolution kernel size of 4; The temperature and pressure fusion vector, the hidden state of the temperature data at the nth moment, and the hidden state of the pressure data at the nth moment are fused to obtain the temperature and pressure feature vectors. The calculation method is: Among them, F is the temperature and pressure feature vector, and MLP() is the multi-layer perceptron operation.

4. The abnormal state monitoring method of a medical sterilizer according to claim 3, characterized in that: The S3 step includes: S31: Calculate the temperature and pressure data difference change and identify the inflection point. The calculation method is: Δt i =t i+1 -t i Δp i =p i+1 -p i time=MLP(MLP(Δt i ,μ,μ part ),Δp i ) Where μ is the global standard deviation of temperature, μ part is the local standard deviation of temperature, k is the local length, Δt i is the temperature difference change at the i-th moment, i is the time index, j is the count index, Δp i is the pressure difference change at the i-th moment, and time is the inflection point; S32: According to the inflection point, the pre-processed temperature and pressure data are divided into three stages: heating, constant temperature and cooling, and the stage labels are added to obtain the temperature and pressure sequences with stage labels, which are represented as T'=[t'1, t'2, ..., t' n ] and P'=[p'1,p'2,…,p' n ]; S33: Construct a gated recurrent unit network with transfer, and extract the background vector of each stage according to the temperature and pressure data with stage labels. The calculation method is: B=GRU Q (T′,ΔT,F) Among them, B is the background vector of each stage, GRU Q () is the gated recurrent unit network operation with transfer; Q = GRU(T′, ΔT, P′, ΔP) Among them, Q is the transit sequence, including the position identifier; ΔT is the temperature difference sequence, and ΔP is the pressure difference sequence; The gated recurrent unit network GRU with transition Q (), taking the gated recurrent unit network GRU as the network basis, according to the position mark in the transit sequence Q, a transit multilayer perceptron is added at the corresponding position of the gated recurrent unit network, and each transit multilayer perceptron divides the gated recurrent unit network into a paragraph.

5. The abnormal state monitoring method of a medical sterilizer according to claim 4, characterized in that: The S4 step includes: S41: Perform stage identification on the temperature and pressure feature vectors to obtain the temperature and pressure feature vectors with stage labels. The calculation method is: F′=MLP(F,t i ,p i ) Among them, F' is the temperature and pressure feature vector with stage labels; S42: Eliminate the background features according to the temperature and pressure feature vectors with stage labels to obtain the alarm feature vector. The calculation method is: f=W3·MLP(W1·F′,W2·B,(W1·F′-W2·B)) Among them, f is the alarm feature vector, W3 is the dimension reduction matrix, W1 and W2 are the first dimension increase matrix and the second dimension increase matrix respectively.

6. The abnormal state monitoring method of a medical sterilizer according to claim 5, characterized in that: The S5 step includes: S51: Calculate the abnormal probability of the medical sterilizer according to the alarm feature vector, and the calculation method is: pro=sigmoid(MLP(f,t i ,p i )) Among them, pro is the abnormal probability of medical sterilizer, sigmoid() sigmoid function; S52: Decode the alarm result and classify the alarm cause. The calculation method is: pro′=softmax(MLP(f,t i ,p i )) Among them, pro' is the probability distribution of alarm reasons, and softmax() is the softmax function operation; S53: Output inspection opinions based on the alarm cause classification results.

7. An abnormal state monitoring system for a medical sterilizer according to any one of claims 1 to 6, characterized in that: include: Sterilizer data processing module: collects temperature and pressure data of medical sterilizer and performs preprocessing to obtain preprocessed temperature and pressure data; Temperature and pressure feature vector extraction module: divides the preprocessed temperature and pressure data into time windows, arranges them into temperature and pressure two-dimensional matrices, and calculates temperature and pressure feature vectors; Background vector extraction module: calculates the difference change of temperature and pressure data, identifies the inflection point, and divides the pre-processed temperature and pressure data into three time stages: heating, constant temperature and cooling, and then extracts the background vector of each stage; Background feature elimination module: eliminates the background features of temperature and pressure feature vectors to obtain alarm feature vectors; Alarm module: Calculate the abnormal probability of the medical sterilizer based on the alarm feature vector, classify the alarm causes, and output inspection opinions.

Images